Saturday 25 December 2010

Research 101

We've had requests to provide the public some tips on how to conduct research of their own. Glad to oblige! Employing the easy process below, you'll be able to model various trends online in fifteen minutes or less.

First things first, though. It's not uncommon to hear "people say" or "most members think that" while these phrases are, in reality, sucked out of a finger, assumptions. Sure, we could all trust our intuition, but it would get messy, especially, when you have two equally assumptuous opinions on the table. Solution? Get to the facts, the objective stuff.

How do you do that? You find the numbers. Why numbers? They are easy to analyse and difficult to misunderstand. When you add 2+4+8 together, you can find their average, maximum value, their order in the sequence, the total, and even come to a conclusion of what number should come next. You can't do that with "dressing" - "snowman" - "goose". When you see 2, it is likely others will see it as a 2, causing less misunderstandings. On the other hand, "dressing" could be understood as getting clothes on or salad dressing. Being on the same page is what counts here.

Also, you may want to have a LOT of numbers. Why? Let's say you're standing in front of a zoo, asking people about the total number of exhibits. You ask a blind person and a small kid, two people. The first person tells you 3, the second - a gazillion. That can't be right. Solution? Ask more people. The theory is very simple: the more numbers you have on your list, the more likely it is that you'll get to the real deal. Sure, the most "reliable" way would be going to the zoo and counting yourself, but it's not that easy if the zoo closes in fifteen minutes and you don't want to spend $20 on a ticket. And if someone asked you about the number, you'll have no way to prove your count is correct. But if you have a list of people vouching for a certain number, majority rules, and it's likely the problem is solved.

Notice that you've been given one example, and some of you may not be convinced. Had there been twenty or fifty examples to justify the need to get many numbers, it would be very likely that everyone would be convinced because different examples would appeal to different people. The beauty of this is a hypothesis, and while it sounds rational, it might not be true. What if all examples are equally dumb? It is likely when only three people work on them. What if these examples contradict one another? See, there is a lot of uncertainty without proper calculations, and if you want to get to the bottom of something, you need to get your hands dirty.

Think about the topic. Do you want to study a trend? Do you want to find what influences something else? Research can tell you which day to post a story to get the most reviews, what are the prospects for your fandom and all other things you've seen in the previous posts. Amazingly, trying to solve one problem usually solves several because you can reuse and adapt your data to show a whole system at work.

TOPIC

We're working in a real environment here, so let's find things you might care about, reviews. Our assumption is that you want reviews and are interested in finding out how to get more reviews. Whether that assumption is true is none of our concern because the purpose of this post is to show you how to conduct research.

Let's make a bet that something influences reviews and they are not written at random. To make things specific, we'll choose one fandom (Sonic the Hedgehog) and one language (English) and a date. Why one fandom? Because that's where a story would be located, and every fandom has different review patterns. When you are ready to post in Sonic the Hedgehog, for instance, you might find it more useful to know the outcome of posting in Sonic the Hedgehog rather than Tetris. More reasons are described in METHOD. As such, our topic would be: "Factors influencing the review count in FanFiction.Net's English Sonic the Hedgehog section in November 2010". Why November? December is not over yet, and November is the latest full month. Stories updated in November must have gotten all the reviews you can count on, both from browsing readers and favorites/alerts.

It's necessary to have a topic written out clearly for yourself and any person, who may want to read your findings. For one, the topic won't let you sidetrack, so you reach a goal set. For two, people will know what to expect from the whole research upon reading the topic's name. Naming your topic too broadly or incorrectly will make you answer questions you didn't ask. If you think it's no big deal to have the topic written wrong, the world of research will be very cruel to you. For instance, if you're looking for review trends of 2009, you may waste time if someone didn't write the year of their research's interest right at the top. Normally, if you don't write the date or the fandom, it is assumed you're doing a general or site-wide search, which is too difficult for this tiny example. When the example is done, though, you will be easily able to make it more up to date and applicable to more fandoms.

Our topic: "Factors influencing the review count in FanFiction.Net's Sonic the Hedgehog section in November 2010".

VARIABLES

What influences a review count (in Sonic the Hedgehog)? The number of chapters, perhaps. The more chapters, the more reviews, we assume, because one person can only review once, and two chapters can mean two reviews from one reader. This might not be true, but our research will be able to answer that, too!

What else? Word count. Stories with less words have less reviews.

Experience? The more experienced the author, the more reviews his or her stories should get. Though, we don't have an experienceometer, so it has to be something else. Author's age? We could ask authors for their age, but they might lie, be unavailable and make us wait too long. Hmm, it seems deciding what variables to use is greatly limited by the ability to obtain the data. Hey, account age might be possible to take to measure experience. The longer the account has been on FFN, the more reviews it should get, we assume. It's possible to get the information from account ID. The higher (newer) the ID, the less reviews an author gets.

Let's add a fourth variable, the number of stories posted on the author's account. The more stories you have now, the more reviews you're going to get, we assume.

We could have added a fictional "yes"/"no" AKA "Boolean" variable. Boolean variables are very useful to turn obscure qualities into numbers. For instance, writer's nationality is boolean when checked by a question like "is the writer American?" In it, "yes" ("American") would be 1 and "no" ("Other country") would be 0. When the variables you have picked logically don't work, add something boolean to set them apart. They can be anything from "acts like a jerk" to "has the word 'honey' on the profile". Just don't let them go dominant in your research.

We're making a quick research here, so that'll be enough variables, four. You may not want to use too many variables in your research because it usually brings certain problems.

Rule of thumb - every variable requires 6 data points. We have 4 variables, so that's a minimum of 4 x 6 = 24 stories in the sample.

METHOD

Now that we've decided the variable we're trying to analyse (review count) and have deciding factors (chapter count, word count, author ID, number of posted stories), it's time to select a method for making the future steps.

Obviously, we're going to gather data based on observation, not a questionnaire. Surveys fail too often, and we don't have to bother anyone by taking notes of what we can see publicly.

We may want to use our research results more times than one, making them practical.

It brings both problems and opportunities. The more you want to predict, the more accurately you want to do it, the higher are the requirements and the less choices you can make.

Let's look at some of the requirements we want to fulfil. We want to apply results of our study to a general audience. By that, it is implied we're using sampling. It's very time consuming to go through all stories on FanFiction.Net (over three-million), so a sample, a part of the whole will do. This part should have the same qualities as the whole.

A visual alternative: you have to draw a specific triangle, but you don't know its angles, only the perimeter (length of the line used to draw it all). You have very little chalk, so that'll have to be a proportionally smaller triangle. One inch of your triangle could mean a hundred inches of the life-size triangle, the qualities (angles/edge length) of which you're trying to determine. This proportion has to be kept for every edge.

The problem is that you don't know how large are any of the angles nor the length of an individual edge, only the perimeter.

Don't worry. There's a magic trick called "randomness". It's difficult to explain, but if you let randomness take the pick for you, you get the most accurate results. This has to do with bias. We're unconsciously biased towards certain numbers, and we can't let that get in our way. Our opinion could only go as far as assuming the logical factors to influence the variable. That's why dice and coins are used as tools of chance.

When making the topic, we saved ourselves a lot of logistics by defining one fandom, and one month, one language. This is our "large" triangle. On FFN it spans from page 23 till 44 of this fandom. For safety, let's reduce our page count to 24 - 43 because the pages may shift while this guide is being written. Every choice has to be justified.

Now, we see a beautifully placed list of stories. Every page has 25 stories. There are 20 pages, so 20 x 25 = 500 stories. Our large triangle's perimeter is 500. Now, we decide the proportion.

This is a crucial moment, so you could pick enough stories to be accurate while not straining yourself with repetition. Another rule of thumb is to have at least 100 data points. If you examine 100 stories, you don't have to prove certain things and can give the data the default treatment. However, you may want to do things more precisely. Commercially popular sample sizes are 250, 500, 1067-1100. The sample size determines the error band. When you have 1100 people/stories examined, the error margin (confidence interval) tends to be 3%. This margin determines the statistical difference. In statistics numbers 43% and 44% are not necessarily different (don't have statistically significant differences) because they might be affected by your error margin. It's possible to determine the interval manually, but I like using this website to do it for me.

Even if you have a small confidence interval (3% is small), there is a chance some freak statistical accident happened and your research doesn't mean squat. It's called a confidence level. In commercial data collection, it ranges from 90% to 99% because you cannot be 100% sure of anything when sampling. The higher the confidence level, the more data points you need. The higher the error margin/interval, the less you need. These two are independent. You may have a 99% certainty level the average review count is 10 +-8% or a 50% certainty level the average review count is 5 +-1%. Confidence levels are, generally, more important. Don't aim for lower than 93% because when you conduct 100 samplings, 7 of them would make no sense at all, and you don't want to be a part of those 7. The max error margin we can tolerate is 10%. There are other factors that matter, but we're aiming at a quickie.

We're going to pick 100 stories, dodging some evidence gathering, at a 95% confidence level, which would give us an 8.8% error margin.

All right, we have the proportion now: 100/500 = 1/5 = 20%. There are two ways we can go now. The easy way in our case is to do systematic sampling, which is, basically, taking every fifth story you see and taking notice of its data. The randomness here comes in having chance decide which story to start from. Since I don't have a 5-point die, I'm going to take five bits of paper, number them from 1 to 5 and let someone pick one of these. The number that is pulled out is going to be which story from the beginning of my sample on page 24 is going to be first, so I go to every fifth after that. Let's assume I did that, and the pulled out number was 1.

The second approach is more difficult in this case, but applicable to more things. Sometimes, it's impossible/unnecessary to know the proportion. FFN "should" have over six-million stories, but it has only three-million. If we hadn't done research before, we wouldn't have known this and, you would think, this would lead to bad samples. Not at all. Sometimes it's impossible to make a list or know the beginning, the end of something. This is where randomness replaces the list without changing any confidence-related issues. Had there been a different number of fanfics on every page (instead of 25 on every one), we would have used Excel's random number generation, and asked it to generate 100 story IDs from 1 to, say, 6 million.

Looks like we're all set for practice.

ANALYSIS IN EXCEL

We're going to work with Excel's 2003 version. First, let's make sure we have what we need. In the top menu, click "Tools" and see if you have "Data Analysis" in the drop-down menu.

If not, go to View-Toolbars-Customise. Click "Commands" Find "Data" and see if you have "Data Analysis" to choose. If you do, just make it visible.

If you don't, we'll need to go to Tools-Add-Ins. Check "Analysis ToolPak - VBA" and/or any other version of the phrase you may have. Press "OK", restart Excel and see if you have "Data Analysis" in "Tools" now. If you don't, your version is either incomplete (use the installation disk, and install Add-Ins for Excel) or you are on a restricted computer.

Moving on. Click Tools-Data Analysis. "Random Number Generation" should be highlighted by default. Excel is clever and knows people first need the random number first. Click it, and you'll see a new window. Pick the drop-down Distribution (in the middle) and pick "Patterned". Now, you're in total control. The number I see on top of page 24 is 576. The number on the bottom of page 43 is 1075. The important part is our proportion 20%, which means every fifth story goes, and we needed 5 bits of paper to decide, whether we start at 576, 577, 578 et cetera. Our paper said 576, so that'll be the first number we write in ("From:").

Fill the window with the following.
Number of variables: 1
Number of random numbers: 100
From: 576 to 1075 in steps of 5
Repeating each number: 1 times
Repeating each sequence: 1 times

Delete the last number if you get 101 results. If you're picky, try "Uniform" in the drop-down of a new "Random Number Generation" window. You just input the range with the rest being identical 1 and 100. Uniform is, generally, a better solution because it requires less input from you at first, and you may have to merely round up the numbers and add 1 if you get two identical numbers after rounding up.

Now, we have the story numbers from the pages we need. We should note the data each story has. If you don't have the time to list the variables, just save links to the 100 stories to check them later. (Instead of making five clicks per story, you'd make only one.) Even if you have the time, save the link or story ID you get upon clicking the stories because page numbers change (that's why we moved from 23 to 24, and the pages did shift since the beginning of this paper). Of course, this is a matter of choice and seriousness.

You have 100 numbers now. I suggest selecting the 100 numbers (not the whole column), pressing CTRL+X, and putting the cursor on cell A2. Press CTRL+V. You should see them now placed one cell lower.

We should do some labelling (that's why we lowered the rank numbers). Write 'y' in cell B1, 'x1 - chapters' in C1, 'x2 - words' in D1, 'x3 - author ID' in E1 and 'x4 - story count' in F1. Add extra labels to make the columns more informative if needed. Consider freezing the first two rows in your sheet by selecting them and going to Window-Freeze panes, so the labels wouldn't get lost. You may notice that 100 stories on the list is more than 24 required by our "times six" rule of thumb. That's good.

What we got to do now is start taking notes. They should look something like this when you finish. Scroll down.

y - x1 - x2 - x3 - x4
9 - 1 - 870 - 1720168 - 3
0 - 1 - 2091 - 2332564 - 35
11 - 4 - 8977 - 1146820 - 4
13 - 2 - 1696 - 2497515 - 8
32 - 12 - 54094 - 370579 - 15
0 - 12 - 9070 - 2600296 - 3
2 - 3 - 2346 - 2625209 - 4
10 - 1 - 942 - 2322399 - 10
0 - 1 - 812 - 1445016 - 27
48 - 14 - 10430 - 2234950 - 2
1 - 1 - 756 - 1247257 - 4
4 - 2 - 6918 - 2254848 - 9
1 - 1 - 828 - 2500706 - 8
11 - 4 - 2851 - 2466270 - 4
51 - 5 - 27418 - 2464934 - 5
23 - 7 - 42338 - 2246255 - 17
32 - 7 - 9075 - 2349427 - 51
0 - 5 - 5611 - 2592567 - 2
23 - 11 - 3932 - 1960339 - 7
6 - 1 - 1326 - 2432493 - 22
2 - 3 - 7584 - 2254848 - 9
62 - 7 - 30210 - 2407962 - 8
36 - 19 - 29653 - 2469814 - 17
19 - 23 - 53349 - 1733388 - 23
4 - 1 - 3013 - 1802183 - 14
1 - 1 - 1480 - 2405648 - 24
3 - 2 - 1646 - 2001585 - 16
11 - 3 - 2300 - 2443927 - 4
2 - 1 - 1772 - 2619494 - 5
1 - 5 - 4977 - 2592556 - 1
16 - 10 - 16627 - 2416048 - 4
2 - 1 - 969 - 998811 - 5
7 - 2 - 3288 - 2621859 - 1
12 - 4 - 2387 - 2572568 - 1
1 - 1 - 1188 - 2576690 - 1
287 - 22 - 106903 - 1263516 - 24
21 - 7 - 9713 - 2229401 - 7
4 - 4 - 3526 - 1842866 - 8
25 - 9 - 6025 - 2418265 - 22
1 - 16 - 12514 - 2581451 - 4
2 - 8 - 5571 - 2324060 - 18
3 - 4 - 8165 - 1055075 - 7
0 - 1 - 641 - 2533529 - 1
0 - 1 - 637 - 2564950 - 12
0 - 1 - 411 - 2434313 - 5
145 - 12 - 51373 - 557082 - 42
1 - 2 - 816 - 2615675 - 1
1 - 1 - 1333 - 2397687 - 3
6 - 1 - 286 - 2363663 - 3
0 - 1 - 653 - 1890945 - 5
0 - 1 - 773 - 2434313 - 5
3 - 3 - 1378 - 2208560 - 9
64 - 23 - 83711 - 909079 - 12
2 - 2 - 2241 - 2603413 - 1
3 - 1 - 4643 - 1314061 - 14
1 - 6 - 807 - 2514303 - 5
0 - 1 - 450 - 2082789 - 3
9 - 1 - 691 - 2497515 - 8
1 - 1 - 201 - 2562978 - 1
6 - 2 - 3249 - 2315797 - 4
165 - 46 - 197328 - 1102393 - 1
3 - 13 - 40438 - 1598320 - 2
25 - 15 - 15107 - 2143219 - 2
33 - 10 - 13654 - 2141369 - 9
20 - 6 - 32769 - 120594 - 3
6 - 9 - 28965 - 1495936 - 22
4 - 1 - 1520 - 2349427 - 51
28 - 7 - 24952 - 2164733 - 8
10 - 8 - 10808 - 2048230 - 2
279 - 30 - 65882 - 1894188 - 10
5 - 1 - 1249 - 2603600 - 5
22 - 14 - 25407 - 2088418 - 1
0 - 2 - 1430 - 2421071 - 1
3 - 1 - 1530 - 1938657 - 7
0 - 1 - 4661 - 2605547 - 2
122 - 21 - 52851 - 1098628 - 5
15 - 2 - 3880 - 2100751 - 19
5 - 3 - 3723 - 2467839 - 2
0 - 2 - 1010 - 2127913 - 4
24 - 15 - 34346 - 1070963 - 5
3 - 1 - 1226 - 2474307 - 10
5 - 1 - 1698 - 2371159 - 11
0 - 2 - 1931 - 2602634 - 2
3 - 1 - 786 - 1890867 - 43
12 - 5 - 6181 - 1685030 - 5
26 - 7 - 6204 - 2133339 - 9
2 - 1 - 963 - 2316070 - 3
54 - 13 - 40760 - 2164733 - 8
8 - 6 - 1502 - 2338442 - 22
0 - 1 - 603 - 2127913 - 4
86 - 15 - 47367 - 1947992 - 15
30 - 11 - 16908 - 2140302 - 4
3 - 3 - 2289 - 2230728 - 6
3 - 11 - 6345 - 2400672 - 1
2 - 1 - 610 - 2547041 - 9
1 - 1 - 1266 - 2404673 - 5
1 - 9 - 6051 - 2596418 - 2
14 - 4 - 4525 - 1543587 - 7
3 - 3 - 3958 - 1514770 - 62
0 - 1 - 494 - 2594903 - 2

Every sample should be publicly available, so others could check your results for validity. It's easy to say "I've done research, surveyed 100,000 people and found that 2 out of 9 are pet owners," but others won't always take your word for it. Samples are usually available on demand as links you can download, not as lists in the middle of your research. The reason you see them here is to save you data collection efforts. By the way, gathering the above took me 35 minutes. This is a slow outcome because I had to click not only to the next page, but also on pen names to find their ID numbers and story counts in another window. Mind you, if you share the burden with two people or don't have to open new windows, you may do it sooner than your media player switches tunes.

Intercorrelation

The "scary part" comes next. It's scary because it has a lot of symbols you probably won't understand and won't need. But first, we lighten up our model. The list of numbers above is the basis of our model, a simplified version of reality. By simplifying it, we may lose some accuracy, but that's okay, because we can always add variables, make the list longer and reach an impractical level of accuracy. You may feel the difference between no reviews and ten reviews, but not 1.04 and 1.06 reviews. Be practical.

By "lighten up" in the previous paragraph, I meant dodging derivatives. You see, we have a dependent variable, our y, the review count. This variable is influenced by what we call "independent variables" x1, x2, x3, x4. While we logically tried to decipher what would be a factor for the review count, we might have, accidentally or otherwise, added variables that depend on one another, are derivatives. Notice how we tried to pick a variable for experience, looking into alternatives. We didn't know for sure whether they were alternatives, but we deemed them so. Statistical analysis allows us to see whether we've included two or more similar alternatives in our model. A model should be efficient and practical, so it's unnecessary to have a variable, which doesn't add value.

We're going to take the BACKWARD procedure. To use it, we need to have all our variables in the table, which we do, and start picking out the variables that don't add value. First, let's do a correlation matrix. In Tools-Data Analysis, pick "Correlation" and select all the data whilst not forgetting to tick "Labels in First Row". Click OK, and you should get a triangle of numbers.

Name: - reviews - chapter c - word c - author ID - story c
reviews - 1 - - - -
chapter c - 0,715994603 - 1 - - -
word c - 0,75572468 - 0,876722508 - 1 - -
author ID - -0,362859097 - -0,37127767 - -0,497448704 - 1 -
story c - 0,14074523 - 0,003728427 - 0,058269805 - -0,208831173 - 1

This matrix/triangle tells us how aligned is one variable with another. The first column explains how attached the dependent variable, our review count, is to our other variables. The higher the coefficient, the better. Anything above 0.8 is so awesome you can draw a straight line and call it a day. In the first column. If anything in other columns (save for the diagonal of 1) is 0.8 or higher (or -0.8), things are bad. It means one independent variable depends on another, they're alternatives. As such, one of them will have to go. And yes, we have that problem. Right in the centre, where "chapter c" meets "word c" we have 0.87. It means one follows the other 87% of the time, and such repetition is redundant. One of them has to go.

How do we decide which? We go to the first column to find which of the two variables "chapter c" or "word c" is a smaller influence to our review count. 0.72 for chapter c vs 0.76 for word c. Therefore, the word count is more important to us than chapter count, and chapter count has got to go. What do we do now? We copy the chapter count column somewhere far, so it wouldn't get lost, and delete it from our main table. My suggestion is to have two sheets with tables, one being main and the other - your work horse, which you edit and mutilate according to what Data Analysis tells you. Arrange your columns comfortably if placement has shifted.

Okay, we got rid of one faulty variable, and there weren't any more interdependent variables. Had there been more than one point above 0.8 or below -0.8 in columns after the first one, we would have needed to remove another variable, the less important of that pair.

Regression analysis

We have just one magic trick left to discover, regression. Explaining what it is in non-math language can be difficult, but it is like a healthy, working generalisation. For instance, you see car tyres as round, you draw them as round, and they are used as an example of roundness. However, if we take a microscope, we'll find the tyre is very uneven, full of dents and little furrows we don't really care about. Regression lets you get to what matters, the essence of a happening, so you are not distracted by something insignificant or scarcely irregular.

Tools-Data Analysis-Regression. Click. We get a very frightening table with lots of tick boxes and input ranges.

Input Y Range: click on the white space after the colon and select the y (review count) column, finishing your selection by the last filled cell. Don't add empty cells, and don't add more than one column to your selection.

Input X Range: select the remaining three columns from the top to the last filled cells. It should be a rectangle with 3 columns and 101 (100 numbers + labels) rows.

Below you see three checkboxes. Tick "Labels" because we have included them this time. You don't have to include labels; Excel will give your variables generic names, but we want clarity here.

Tick "Confidence Level", and set it for 95%. It should be also the default number.

Never ever tick "Constant is Zero" or our car tyre model may turn into a square. If you're curious, ticking that would kill one number responsible for evening things out.

Don't touch anything else in the window, and just click "OK". You have a new sheet. Rename it to "regression" if you want. On top of the spreadsheet, you have SUMMARY OUTPUT and three weird tables, each with more columns than the previous. We'll be working only with the third one, but the other two are useful, too.

The top one tells you, basically, one thing. You may have seen "R2" or "R squared" mentioned in our previous releases. It is a coefficient, which explains how well your variables determine changes. In our case, how well the word count, author ID and story count determine the review count. This number ranges from 1 to 0, and anything above 0.8 is awesome. Anything below 0.3 is horrible. In our case, Multiple R is 0.76, which we disragard, and look at the second row R Square. It's 0.58. This means that if you get 100 extra reviews, 58 of them can be explained by how many words you used, how many stories you wrote and when you joined the site. 42 come from factors we have missed.

Now, when you have a lower R Square, below 0.5, it can mean two things: you've missed some important factor while brainstorming or there is a problem with the numbers you've attained. There are methods on refining your data, but our example looks good, so we won't need them.

Have a look at the second table creepily labelled ANOVA. On its right edge, you see Significance F. Let's call it "the fail factor". It's 4.06 divided by a number with 18 zeros or "4,06E-18" (0.000...0406). It's a very small number, which means our fail factor won't bother the results. When you see this number grow big, reaching 0.1 and the like, it means your research is destined to fail and you might as well give up because making it work would be as difficult as heart surgery. The fail factor applies not to one variable, but to everything at once, and any connections you make are a coincidence, a fake. But let's put a smile back on your face because our model is safe.

A bit robust, though. We're going to have to butcher it a bit. Third table. There are three methods we can use. All of them should (almost always) give you the same results. Before we do anything, though, look at the row that says "Intercept", the first row of numbers in the third table. Highlight it in yellow, make the text white and do whatever you need to ignore what's written there. Once that is done, here's what we're going to do: see if there are irrelevant variables in the model. Sometimes, a variable is not important enough, does not cause enough changes to your review count, so we may safely kick it out. We determine if any variables are useless, and carefully puncture them out.

Three methods for removing weak variables:

t Stat column. Rule of thumb: any value between -2 and 2 (higher than -2 but lower than 2 [0.7, for instance]) means you should highlight the number's row red, ready to kick it out.

P-value column. It shows the possibility for a particular variable being useless. See your confidence level (we have 95% or 0.95 without the percentage). If the P-value is higher than 1 - confidence level (we have 1-0.95 = 0.05), highlight the row red, ready to kick it out.

Lower 95%-Upper 95%. See if they have different signs (one is positive and one is negative). If they do, highlight red.

The most reliable is the third one because it's easy to see the difference between number signs, but any one of these is enough. If you check the table (word c, author ID and story c rows), all three tests would have given you the same results. word c has a high t Stat value, low P-value (E-17 means divided by a huge number), and Lower 95%, Upper 95% have the same sign.

Author ID has a low t Stat, only 0.545, lower than 2, a P-value higher than 0.05, and signs are different on the Lower-Upper columns.

Story c has 1.55 t Stat, lower than 2, but higher than what Author ID has. P-value is 0.12, higher than 0.05, but lower than what Author ID has. Lower-Upper columns have different signs.

Looks like Author ID and Story c would be highlighted red for removal, but we don't remove them both. Like when we ditched chapter count, we have to cull them one at a time, the least important first. Chances are both will end up as totally unimportant, but when we remove just one variable, the whole model might change.

As you could see, The Upper-Lower test with different signs works as far as telling you "there is/isn't a problem" (boolean), and you can use either t Stat or P-value for deciding which variable is removed. In our case, let's use t Stat. Author ID has a lower t Stat, so we go to our working table, and remove that column.

We are now down to two independent variables, word c and story c, along with our review count.

Tools-Data Analysis-Regression.

Repeat the process. Review column from top to the last number in Y Range, and word c, story c columns in X Range. Tick Labels, Tick Confidence Level 95, click OK.

Once again, we see three tables. Let's look at R Square. It's still 0.58, which means ditching author ID did not lose us even one percent of usefulness. It won't be missed. We skip the second table and go right to the third. Feeling fast, let's go for the P-value test. Only one P-value is higher than 1-0.95=0.05, story c. 0.14>0.05. The t Stat is also lower than 2, so we highlight the row red, and go to the working table.

Delete the "story c" column (should be the one on the right). Now, we're down to just reviews and "word c", two columns. Tools-Data Analysis-Regression. Repeat the steps, only the X Range will be one column instead of two. Click "OK".

And we have another sheet. Looking at the first table R Square is 0.57 (was 0.58). Ah, so we did lose something with the story count. It may mean that the number of stories you write has an influence to your review count, but it is so insignificant, including it will only make our calculations complicated for very small perks. In any case, the drop was just 0.01 because the t Stat and other tests called that variable insignificant. Had you accidentally kicked an important variable, R Square would have dwindled...by a third or something.

So, what do we have now? Obviously, t Stat and other tests are okay. We're out of insignificant and useless variables. Oh, and look at the corner of the second table! Our fail factor has become lower. It's 1.02E-19. Used to be 4.06E-18. 40 times smaller. Nearly 98% of our fail factor was contributed by the variables we kicked.

Now, we can draw a rule for the review count in FanFiction.Net's Sonic the Hedgehog section in November, 2010.

y=0.001326x1 + 2.46 + e

y - review count
x1- word count
e - compulsory random error, for all the forces we did not account for

As you can see, the function is linear. By default, you should get 2 reviews in Sonic the Hedgehog. Every word you write, according to this function, adds a thousandth of a review. This means, if you write a thousand words, you, statistically, get 3 reviews. "Statistically" means "on average". This equation is a pretty good tool to measure how well your story is faring against works of others.

Right now, you can make an estimate on your stories written in that fandom. You know what influences the review count, and how many reviews you can expect when you start writing there. If you're a review hog, have a group of friends analyse several fandoms, and join the one, which gives you more reviews per written word.

CONCLUSION

Conclusions are necessary in research. They must be brief and informative because some people like spoilers, and skip to the results.

In Sonic the Hedgehog of FanFiction.Net during November, 2010, the total word count influenced the total review count. There was a positive linear relationship, where every extra word added a thousandth of a review.

The number of submitted stories and author ID were irrelevant to the total review count. Neither was the chapter count, an alternative of the word count.

EXTRAS

Here is a bonus for the curious. You did see that our linear function was described as "pretty good". What if there is a better way? Surely, if someone writes 50,000 in one chapter, they can't possibly get as many reviews as someone with a more reasonable 5,000? Nobody reads 50k in one chapter, you may even think. And your thoughts may be right. Regression analysis gives us linear results, and the line can go either up or down indefinitely from start to finish. We could build a curve.

However, the problem with curves is that the more complicated they are, the more time it takes to put one to use. That in mind, we go to our working table, with just two variables review count and word count. We're going to draw a chart. First, move the reviews column to be on the right of the word count column. We need it to dodge some messy misconceptions on Excel's part.

Insert-Chart. Pick XY (Scatter). It's very important that you use the scattered dot matrix. Upon clicking it, select the default subtype without any connections. Click Next. In the window that appears, you may have what you need already, but, to be sure, look at Data range (below the chart), erase it, and select two columns, the review count and the word count. Make sure the series are in Columns (radio selector). Click either "Next" or "Finish" because we should have everything now.

You should see a weird mess of dots, lots near the zero point, and just a few far from the beginning. Left-click on one of the dots. Several of them should light up yellow. Right-click on the dot, and select "Add Trendline". A new window should appear. You should see different curve types you can select. The linear is the default one, and it would have been identical to the equation above. We select the top right one, Polynomial. Most of the time, it's the most useful curve type. Now, go to Options on top of the window. You should see three tick boxes. Tick the third one, Display R-squared value. Go back to Type, on top of the Add Trendline window. Look at "Order" next to the Polynomial curve.

2 order gives you a parabola. 3 gets a cubical parabola and so on. The higher the order, the more steeply it will rise. Right now, we have to decide, which order is the optimal one. The optimum is somewhat arbitrary. If a higher order does not give you a "sufficient" increase in the R-square value, stick to the current one. If you recall, our linear trend gave us a 0.57 value, so 43% of all changes are a mystery. Let's pick order 2 and click "OK". A curve appears. It reaches to the bottom at a certain point, and R Square is 0.62. That's a 5% increase. We've found a better estimate for our function, but is there an even better one?

Repeat the steps: left-click dot, right-click-select Add Trendline, pick Polynomial - Options, tick Display R-squared value on chart - Type, pick order 3, OK. Now, it says 0.701. Eight percent. We've gone up from 0.57 to 0.701 in total only by changing the curve's form. Truth is definitely out there. Usually, it's a sign that going higher is useless, but you can try orders 4 and 5. Make the graph larger, so all the numbers fit on-screen. Order 4 gave 0.707, less than one percent. It's reasonable to assume things only get worse from there. Order 5 is too complicated, and too useless.

Order 4 is going to be a pretty long equation, and minuscule extra accuracy isn't worth the high-power equations. Order 3 is good, but it will lead to an irrational end (study a 3rd degree parabola). Order 2 isn't bad, but the gains aren't huge either. Let's leave it at order 3. The nearly 10% increase in accuracy is very nice. Right-click the second lowest (order 3) trend line, Click Format Trendline, go to Options and tick Display equation on chart. OK.

It would be: y=-2E-13x^3+4E-8x^2-0.0002x+5,436

This one, while better suited to describe the review count in general, has two problems.

1. It cannot be used for stories longer than 170k.
2. It overappreciates the minimal number of reviews a story can get.

As such, it is good in theory, but, in practice, stories are shorter, and their brevity calls for a different system of reviews. For this reason, let's also include the 2nd degree polynomial function:

y=-5E-9x^2+0,002x-2,7011

Interestingly, the number of reviews would drop after a story gets more than 200k words. While reasonable, this function has an accuracy problem, compared to the 3rd order. The solutions can be mind-boggling, like taking one function for word counts 0 to 10,000 and another for 10,001+. Less exotically, once we decide to get to the bottom of the issue and stop tolerating discrepancies, we need to not only drop variables, but also drop data points. Without going into two complicated tests, pick Tools-Data Analysis-Descriptive Statistics. Select the two variables, labels in first row. Tick summary statistics and Kth Largest, Kth Smallest, both set to 1. OK. There should be a table with four columns, two per variable. We're going anomaly-hunting.

We need two things, the top value, Mean, and Standard Deviation, row 7. Add three times Standard Deviation to the Mean. For word count, that would be 13,727+3*26,726=93,905. Why are we doing this? Anything above this value is an anomaly, and only 0.3% of all values can be higher than this without messing up our calculations. Since we have 100 data points, any one word count above 93.9k is an anomaly. What do we do to anomalies? We delete them. What do we get afterwards? A headache, looping back to the charts. That's the beauty of statistics: while 80% of all accuracy requires 20% of effort, getting 20% more, you guessed it, makes you sweat a whole 80%.

Hopefully, this has been an interesting enough adventure in the realm of online research. Calculating the basics really takes but a few minutes, but when the world gets you stumped in conclusions that seem impossible, you may spend hours. And when you think this is ludicrous, ask Facebook or Google if there's a better way to get into your head.

Merry Christmas, folks!

Friday 1 October 2010

Erased Accounts

We're not idle here, don't worry. Since FanFiction.Net has been glitchy as of late, it was next to impossible to publish a list of purged user accounts. Likewise, it was difficult to create a list of good stories with the most objective criteria available.

As of today, the pending analysis of good fan fictions has a 90% confidence level, which is insufficient for further group analysis. No conclusions are presented from this research to prevent erroneous assumptions.

However, we have a static list of accounts deleted in the years 1998 (since October), 1999, 2000 and the first half of the year 2001. Here is the list. 4700 user accounts were purged in this term. It is an accurate list derived from observation for those dates with 98.7% of all accounts from ID 1 to ID 80,000 checked. It is not suggested that you make site-wide conclusions for the current situation, as the domain's growth and guideline changes ensued in 2002 and 2004, which created conditions that would render the numbers attained for the first 80k inapplicable for later years.

The 0.85%, as attained via our earlier sample remains as the accurate number for deleted accounts. Yes, approximately 1 out of 100 accounts is deleted on FFN. If you have 1000 favourite authors, 85 of them will cease to exist due to infringement. Should you contest this number, the accounts in our random sample are provided in a separate file (like in the previous post).

Sunday 18 July 2010

FanFiction.Net Member Statistics

The research team is proud to present you first numerics from our user-related queries. This post answers many questions, including the following:

-How many writers are there on FFN?
-How long will you stay on FFN?
-How many stories do they write?
-How many users are deleted from FFN for infringement of ToS?
-How quickly does FFN grow?
-How many readers you should expect for a story?

First, we must present the methodology, though. The study consisted of generating 1100 random user account IDs spanning from 1 to 2,400,000 (source data at the bottom). It allows us to generate representative unbiased results at a 95.34% confidence level and a 3% error margin. The list has been generated on the 29th of June 2010. Therefore, we have included all accounts that have been registered, enabled and fully functional, without restrictions of story creation or profile/review posting.

Now, the definitions. You will see the following criteria used in this post:

Empty account: any account that does not host stories uploaded by the owner. In layman terms, there are no stories posted in this account. There may be favourites. Here and here are examples of accounts dubbed 'empty'. Conversely, this is not an empty account.

Active/alive account: any account that has shown signs of life in the past six months, from January 1, 2010. This may be the following: updating or posting a story OR updating the profile OR adding a favourite story OR reviewing a favourite story in the past six months. For example, these two accounts are called 'active' or 'alive' in this post. In the case of the second example, please check the favourites. As long as at least one criterion is met, it is active. Those, who have joined fan fiction in the year 2010 are active by default due to a professional grace period to create a story.

Inactive/dead account: any account that does not meet the active/alive criterion above. Here are two examples.

Deleted account: any user ID that shows the following or similar message "User does not exist or is no longer an active member."

Main Part

You probably recall that FFN has ~3,300,000 stories from our last research (number rounded up to accommodate growth since the previous post), which is 53% of all posted material, with the other 47% deleted. Keep this in mind for a moment.

In the sample of 1100, we have discovered 742 empty accounts, which means, via representativity, only 32.5% of all FanFiction.Net users have stories posted. How does that transfer into general numbers? In a population of 2,400,000 members 781,000 have stories (4.2 stories per account with a story on or 1.375 stories per every member), while the remaining 1,619,000 do not participate in adding content. Two thirds of all members are pure readers, or so it may seem. If it were correct, we could say that 1 writer has 3 dedicated readers on average, if we assume writers themselves read. However, it's not that simple.

Some accounts are plain dead. How many? In a sample of 1100, 855 accounts were inactive, and showed no signs of life in the year 2010. What does that mean for FFN? 78% of all accounts on FanFiction.Net are dead. Less than a fourth, or 22% is currently at your disposal, or 528,000, which is less than the number of accounts with stories on them.

The fun part begins now. How many writers are active? Who could you expect updates from? We connect the overlapping clauses of 'active' and 'not empty'. In a sample of 1100, 130 accounts showed signs of life and had stories on. It translates into: 12% of all accounts on FFN have at least one published story and are actively engaged in fandom activity. 88% of members on FFN are currently not shaping any fandom. As for those, who do, there are 283,000 of them. We have found out that there are 5259 fandoms on FFN, which would mean 54 people keep a fandom alive in the course of 6 months.

On average, no more than 54 people appear in a fandom over six months. How many new people is that per day? 0.3 of a person drops into an average fandom. An average fandom has 681 stories. A median fandom, the one in the middle, which ditches the enormous influence of HP with 0.5 million stories, has 16. That was a bit of extra information, and we now return to users.

One aspect of FFN particularly interested the research team, the number of account deletions by the administrator. 0.73% was the number we acquired. That's less than 1 in 100. However, let us convert that into raw numbers. 17,500. We add an arbitrary 3000 to that number because accounts from 1 to 3000 are unavailable, and the account number generator did not account for it. What do we get? Since September 1998 fanfiction deleted over 20,500 users for infringement. It stands for 0.85% of all users. 4.75 accounts are deleted per day on average, a very modest number because we disregard deletions impossible to document and test easily, like those attributed to policy changes (for instance, when MSTs were deemed unwelcome).

Who would that be? Blacklisted people: spammers, trolls, plagiarists, other infringers. They missed a few trying to use FFN as an advertising venue here and here.

By now, you already know how many account totals are there. It's time to break them into a time series and give you an understanding of how quickly FFN grows.

A table below tackles this issue. We need to explain the columns for complete clarity:

Total: the last account ID created in the year (AKA summary number of accounts created until December 31, all years including the one in the row [accounts made this year + all accounts made in the previous years])
Change: number of accounts that were created in the year in question
Growth%: how much accounts FFN gained in comparison to the previous year, excluding accounts created in the previous years.
CChange%: chained value of change. The ratio of Change (this year to last) divided by the ratio of Total. Answers how quicker (above 1)/slower(below 1) grew this year in comparison with the previous, acceleration.
Middle: the date when half of the annual growth is reached, 50% of accounts created in that year are already present by this date.

Year - Total - Change - Growth% - CChange - Middle
1999* - 6749 - ... - ... - ... - ...
2000 - 33,090 - 26,620 - 411.4 - ...
2001 - 147,200 - 114,110 - 344.8 - 0.19
2002 - 318,900 - 171,700 - 116.6 - 0.16
2003 - 512,000 - 193100 - 60.6 - 0.32 - June 22
2004 - 733000 - 221000 - 43.2 - 0.5 - June 13
2005 - 959000 - 226000 - 30.8 - 0.55 - June 29
2006 - 1188200 - 229200 - 23.9 - 0.63 - June 21
2007 - 1458900 - 270700 - 22.8 - 0.78 - June 17
2008 - 1788000 - 329100 - 22.6 - 0.81 - June 3
2009 - 2238000 - 450000 - 25.2 - 0.89 - May 31
2010** - 2680000 - 442000 - 19.8 - 0.66 - July 21

*Accounts created in 1998 added. It is impossible to tell when exactly a person joined before 2000-01-07.
**estimated, based on the first 6 months.

Before we begin analysing the data, there is an explanation for our 2010 estimate. We calculated it according to seasons, not a plain average. Based on our calculations, by June 21 the site receives 50% of its annual account growth spurt. This means that slightly more accounts are created in the first half of the year, than in the next six months. Site-wide, there is no reason to assume 'big' events like the release of a movie or a new popular book create significant fluctuations. Years before 2002 were not included due to volatility while the site was still young.

Now, let's carry on with the examination. As you can see in the Total column, the site is growing every year. Rational. The Change column shows that an increasing number of people joins the site up to 2010, with the period from 2004 till 2006 being stable in terms of Change. Things become trickier with Growth% and CChange. Some of you may be confused why a site which is growing more and more in raw numbers seems to score poorly in the last two columns. The explanation is as follows: as the site grows, it needs a larger number of new accounts to sustain itself. Simple example: site with 1000 accounts made in the previous year gets 1000 more this year. Next year, it will be 2000 accounts. If the site grows another 1000 next year, this 1000 will be relatively smaller (50% vs 100%) than the first. The same is happening to FFN, as it gains a similar number of accounts that weigh less and less.

The rate of acceleration or slowing down is most visible in CChange. Not a single value is higher than 1, which means the site never grew faster than the year before. On the contrary, the rate of slowing down, the closer to zero the less momentum the site gains compared to last year. From 2000 till 2009, deceleration (slowing down) was becoming closer to 1, a sustainable equilibrium point, but the year 2010 returns us to levels of 2006.

In layman terms, imagine two speeding cars. One of them is the site, and the other is 1, how the site did last year. The other car is a ghost/time challenge type that repeats the race as it was before. The ghost reaches the finish line first every time because your car never reaches the value of 1. You lose one race. Next time, the ghost repeats how you raced the time you lost. And again. Meaning, every race the ghost is slower, repeating your losses. You keep losing, though. While you do, you notice that if at first you lost by a long shot, after several runs, you still lose, but 1 is a lot closer.

If it weren't for 2010, a great gap in a seemingly fluent continuity, we could have made an obvious conclusion that FFN will, eventually, grow faster, and its growth will be bigger both in volume and ratio that volume takes in the whole (your car will start a winning streak).

Regression analysis showed that there is a polynomial relationship between time and growth. Linearly, there is a positive relationship and a linear trendline would claim that the site will reach CChange=1 in 2012. With an R^2=0.825.

A polynomial trend fits better, with R^2=0.9 for the parabola. It means that the function you will see below 'catches' 90% of all vibrations that our growth spurt (CChange) makes, and best describes fluctuations in growth on FFN. What does that R^2 mean? 90% of all growth fluctuations are explained by time in the function below.

y = -0,0094x^2 + 0,218x - 0,4813

y - CChange value

x - number of years since 1998 (0, 1, 2, et cetera)

Basically, this function allows us to calculate the future of FFN. What is it? Well, according to this, the CChange value will be 0 when the site reaches 21 years of age or by year 2019. This is the scenario we follow if the site does not gain momentum by 2012. If we employed descriptive statistics, any CChange above 0.779 and under 0.3 would have been considered anomalous (the rule of three standard errors). Removing those values gives us a more pessimistic, yet less accurate, picture of these events. Reaching 1 would take three years longer linearly, and negative CChange would also be acquired sooner in more reliable polynomial models. Our choice on extrapolation is based on the principle of numeric accuracy, provided other factors remain static. Surely, clever website management and an increased interest in fan fiction as a concept is bound to change the end result. It does, however, suggest that site administration would avoid the trend described in this exercise.

As a final part of this piece of research, we would like to address a number we have shown you before 12%, the number of accounts that have stories on and currently participate in fandom. Another 10% are active readers and do not have any stories posted. This is a general number, though, and we are sure You are more curious to know where do you stand with your peers rather than the whole site.

Below is a table with the following columns:
Year: year of joining.
Full: possibility% that your account is still active and has stories if you joined in the designated year
Empty: possibility% that your account is still active, but has no stories, if you joined in the designated year
Full stays: the probability% that if you have stayed until July 2010, you have stories on

We start from the year 2002, when initial FFN volatility abated. Empty in 2010 is skipped.

Year - Full - Empty - Full stays
2002 - 6.4 - 2.5 - 71.4
2003 - 8.5 - 1.1 - 88.9
2004 - 3.7 - 1.9 - 66.7
2005 - 5.7 - 2.3 - 71.4
2006 - 9.1 - 2.0 - 81.8
2007 - 9.1 - 5.8 - 61.1
2008 - 16.2 - 2.8 - 85.2
2009 - 18.6 - 21.3 - 46.6
2010 - 28.4

Interestingly, you are more likely to stay over a year on FFN if you have stories and are a writer than if you were just a reader. However, you have an equal chance of staying on FFN for a year, writer or reader alike. Regardless, if you join FFN, chances are you will not write a story and you will not be on the site longer than six months.

Even if you have written a story, it is most probable that you will not be on the site longer than six months. This is a generous time period, and it could be that six months is the most probable activity lifespan because it is the starting point and anything smaller does not exist in this part.

We have worked on regression to give you an easy way to calculate the perspectives of staying on FFN. A fifth degree polynomial function seemed to have the biggest R^2=0.99. Amusingly, the probability would go down to negative 1700% very quickly after 8 years, so we had to switch to a simpler parabolic function with R^2=0.96.

Y=0,0218x2 - 0,2603x + 0,961

x - the number of years you have/are intending to stay on FFN. (Works for values up to 10 years).

y - % that you will stay.

According to the given function, it is least likely that you will stay on FFN for 6 years. Thus, yes, more likely that it will be 7 or 8. We attribute this to some form of fandom patriotism the earliest members have expressed to the site. A more precise function would have to include account deletions, which should, in reality, lower active account rates (remember the 3000 first accounts?) and the possibility of staying much longer than 8 years. In any case, the function above is presented for your amusement. A more informative variant is below.

We understand that it might be difficult to imagine the contextual difference between 6% and 9% dominant in the previous table. For this reason, we have made a coefficient, so 28.4%=1. This way, you will see more clearly how many active accounts die away, and how many stay active.

8 years 23%
7 years 30%
6 years 13%
5 years 20%
4 years 32%
3 years 32%
2 years 57%
1 year 65%
0 years 100%

The process can be done further if you want to see how many % of 65% et cetera die in the following years.

Active fanfic participating accounts (those that make up 12% on the site, remember that) lose 35% of their numbers in the first year. The second most rapid drop is in 3 years, but people who tend to stay 3 years are prone to staying 4. The last accurate piece of data that coerces with the trend: the more time passes, the less people stay, is 6 years. Only 1/8 of the people who are active writers right after joining remain this way. 7/8 chip off during the trip. As such, the number of permanent contributors (who stay on the site for years) increases as FFN grows. There is only one 'but': the increase is majorly consumed by users abandoning their accounts.

Those, who have spent less than 6 months account for 6.5% (29.5%) of the 22% of people that are active in any way. Another 7.3% (33.1%) come from those, who have spent more than a year. As such, it is reasonable to say that almost two thirds of the site is actively inhabited by inexperienced account owners, rated 'fans' in forums. So-called 'fanatics' make up a third of the active population, a third that spans since 1998 till the beginning of 2009. On the one hand, it is peculiar that the amount of active newbies (writers or just readers) is almost equal to that of 'fanatics'. On the other, it should make quality control out of the question. Why does it not even out? A question we leave in your hands, dear readers.

Conclusion

Unless FFN manages to speed up its growth potential, those 12% that currently shape the fandom will not be enough, especially because ~5 accounts are deleted every day. The site needs to replace more than 35% of active users every year, and 2010 so far looks the most challenging yet. More dedication, fellow fans. May the concept of fan fiction prosper.

Added: here is a list of user accounts in our sample.

Question: What about people who just go to forums, aren't they active?
Answer: They do not make use of the site's core service as a fan fiction archive. If you don't write or read stories, you are considered inactive. The only way a forum goer could be included as active (provided they have no stories or favourites) is if they updated their profile this year.

Wednesday 7 July 2010

Most Popular Categories

This post is to clear confusion on FFN about what is popular on FanFiction.Net, what is not, and why. All statements you will see in our report are based on raw point data, collected on 29th June, 2010. This means that everything has been taken in machine fashion directly from the site in the method known as observation, not via sample by omitting fandoms. (It was scooped by looking at the numbers, for the younger readers.)

As such, the presented data has a 100% confidence level. However, we understand the value of server delays and are including an arbitrary 3% error margin because the data is taken from the top-category view, not by trawling inside every fandom. If you recall from the previous post, top-category views show a slightly bigger number of stories (up to 5% for some fandoms) for active fandoms (with over 50 stories), so this is included due to FFN site dynamics as a precaution, despite the inclusion making no difference statistically. This is made necessary further because a part of our target audience has not passed a statistics course.

To make this more interesting, we suggest that everyone takes a guess, which top category is more popular: Anime/Manga, Books, Games, TV shows et cetera, from the list of 10 on the front page.

Depending on your age, the answer is probably 'Games' or 'Books'. The answer would not be far from truth, but not even Harry Potter, the biggest fandom on the site gives Books the top spot. Conversely, it's not the combination of Kingdom Hearts, Pokemon and other games, all with the biggest forums on FFN.

The largest top-level category on FanFiction.Net is Anime/Manga with over 1,062,835 publicly available stories. It also has numerous subcategories/fandoms, 955. Despite this, a third of them (over 300) has under 10 stories, with the bulk concentrated in Naruto 240,635 and Inuyasha 93,196.

If you recall, FFN has approximately 3,200,000 live stories, which means every third story found on FFN is related to Anime/Manga. Why? We can't answer that just yet like we can't tell you why only 1 in 50 writers becomes a Beta Reader.

Anime and Manga have #1. Now, for all Harry Potter, Twilight, LotR, Warriors, PJO et cetera fandoms, you are not unimportant. Books have a firm #2 with 811,044 live stories. Respectively, 461,311 and 150,708 belong to Harry Potter and Twilight. Let's dwell on these two for a moment. The HP fandom is marginally three times as big as Twilight. The underdog may claim this exists because Harry Potter has been a lot longer than Twilight. Making matters fair, that would mean Twilight would be as popular as Harry Potter if they were of the same age.

What's real and what's not? The first HP book has been released in 1997, 13 years from now. The first Twilight book has been released in 2005, 5 years from now. One might exclaim: "Ah hah! Two years is a very small time, so they must be equally popular!" Let's do the math. HP is 2.6 times older than Twilight. Had they been released at the same time, Twilight would now have 391,000 stories, 70,000 behind HP. How big/small of a difference is that? That's almost two LotR fandoms and the total number of new books released in Spain annually.

We return to weights. If the largest fandom in Anime/Manga, Naruto has 240,000 stories, a fourth of the total Anime/Manga, HP has 461,000, way over half of all Book-related fiction accessible on FFN. One may think, seeing that books are #2, more popular than Games, Comics, TV shows (some of which summed up), the world of fiction is into literature fandoms. False. Anime/Manga is popular because there are many fandoms. Books is big because there are many HP. In layman terms, it would be sensible to rename 'Books' into Harry Potter & Twilight, pop reads, which can only scratch the surface of, say, critically acclaimed classical literature. The audience on FFN could have been assumed as an active participant in literature fandoms. It is, however, an active participant in HP and Twilight-level literature fandoms.

Moving on to #3, which is TV shows at 580,596. Curiously, their outlook is similar to that of Anime, with a third of all fandoms having under 10 stories, and there being multiple weight leaders. 15 fandoms take the range from 40k to 10k. In Anime, 20 fandoms have over 10k stories. In Books, 4 fandoms have more than 10,000 stories.

One may want to run an economic monopoly concentration index formula on these numbers. In case it is viable, we present the number of fandoms in the top categories.

Anime/Manga: 1,062,835 stories; 955 fandoms; 20 fandoms have above 10,000 stories
Books: 811,044 stories; 1138 fandoms; 4 fandoms have above 10,000 stories
TV: 580,596 stories; 1013 fandoms; 15 fandoms have above 10,000 stories

Additional research is suggested for the curious: remove all the popular fandoms that add substantial weight to the category (have above 10,000 stories) and make an account of how much dead weight, or impopular fandoms, every top level category has.

At the moment, numbers suggest that the Anime/Manga is the healthiest fandom. Why? 1. It has more stories than others. 2. It has less fandoms. 3. It has more popular fandoms than Books and TV altogether. 4. It is least threatened by C&D (cease and desist) letters.

The fourth one is important. If a cease and desist letter is sent to, say Harry Potter fans, forbidding them to write fan fiction, books would drop dramatically from 811,044 to 349,733. If the same happened to an Anime/Manga fandom, the most loss it would have would be 240,635, less than a quarter of its size. Same applies to TV.

Let's not ignore other fandoms. Below is a limited table/list of top categories without crossovers. Crossovers were counted in our summary of all stories on FFN, but they produce confusing data in the way they are organised, belonging to several fandoms at the same time. The list below is made for clarity purposes.

Name - Story number - Fandom number - Fandoms above 10k - Top fandom

Anime: 1,062,835 - 955 - 20 - Naruto
Books: 811,044 - 1138 - 4 - Harry Potter
TV: 580,596 - 1013 - 15 - Buffy: The Vampire Slayer
Games: 269,261 - 614 - 6 - Kingdom Hearts
Cartoons: 192,918 - 320 - 5 - Teen Titans
Movies: 125,000 - 943 - 4 - Star Wars
Misc: 105,500 - 34 - 2 - Wrestling
Comics: 33,824 - 123 - 0 (8 above 1000) - X-Men
Plays: 15,300 - 85 - 0 (5 above 1000) - RENT

The following information is suggested for further study: how many fandoms are uninhabited (have below 10 stories), how much is that divided by the number of fandoms in the category?

An explanation should follow for the last two categories, Comics and Plays. Plays, for example, have been included much later than other top categories, setting them aside. Also, since they do not exceed 100,000 stories and it is rational to use a proportion size, the active fandom definition is adapted to them as 1000.

As always, present your questions, solicit ideas. This blog is interactive, and we will cover your topics of interest. Coming up next: how many writers does FFN really have?

Tuesday 6 July 2010

FanFiction.Net story totals

Good news!

Our research venture has completed gathering data about site-wide story numbers. This post explains how many stories FanFiction.Net (FFN) really has.

The data in our evaluations has been generated based on the total number of stories posted on June 25th, 2010. The gathered data has been in processing since June 25th, 2010 till June 30th, 2010. We treat it as spatial or point collection; 5 days = 1 instance.

At the time of collection, there has been a total of 6,085,534 registered story entries, based on the newest registered story number in the Just In section on June 25th, 2010.[1].

However, we understand that some stories are deleted, and their ID number is not taken out from the database to be recycled for a new story.[2] Instead, the list carries on, and every newly posted story receives a number higher than the previous.

(An additional explanation for younger readers: you submit a story, and it gets an ID number in FFN's database, so everyone could easily find them. Let's say your ID is 123. If you know that, you can easily make a link without having to copy anything because all stories on FFN have http://www.fanfiction.net/s/*your story ID*. When someone posts a story right after you, their ID is 124, then 125, 126 and so on and so forth. Say, the site got to story number 140, but story 128 has been deemed illegal because it was about living actors, and deleted by the FFN staff, so nobody would sue. What do we have? We have numbers from 1 till 140, but 128 has been deleted. You can't know it has been deleted, by the way, because you're not the writer, and the only way to find out is to check. There are now 139 stories on the site even though it looks like there is 140. Thing is, on a site as big as FFN, you can't just guess how many numbers are 'blank' like that.)

It is the main reason for this analysis: the number FanFiction.Net presents to you is not the total number of stories it has at the moment, but a sum of all fanworks it had at every moment of time available to the public. The key term is 'available to the public' because FFN, according to their ToS, keeps server copies of user submissions. It is reasonable to assume that the real number of stories we can see now (dated June 25th, 2010) is not over 6 million.

We're implementing two methods to reach the data. The first is doing an account of all stories present in all ten top categories and crossovers such as this. Surely, it is a lot of very repetitive and dull labour, but it gives us the exact number, which is: 3,256,278 stories.

As of June 25th, 2010 there are 3,256,278 stories noted as accessible to the public on FanFiction.Net.

This is an accurate number, but it is not 100% of what the story number has been. Why? We made a top category account, without having to rummage through every single fandom, opening it like this. Why is this important? The number of stories in the top category window is always bigger (or even, when the fandom is inactive [has less than 50 stories]) than the real number of fictions one can browse inside the category. The researchers cannot provide you a firm answer on this discrepancy, but it may be attributed to dynamics of stories being deleted at a slower rate than they are added (for example, if you upload a story by mistake, and delete it, you raise the top category number of stories, and it stays above the real number even though you can no longer find the story, a server delay).

It has been determined that, depending on the fandom, the real number is from 0,19% to 5% smaller than the one provided. In large categories, the weight of which forces the researchers to consider them, this number teeters closer to the first value. Now, it might not seem substantial, but Twilight with its 150,000 uploads may have up to 2000 dead stories counted as alive every day. To be completely fair to the estimate, we are multiplying the number by an arbitrary 0.987 coefficient, which best describes the current number of stories, as seen in ten most popular, story-wise, subcategories of Books, Anime and others, except crossovers. Since they make up the trending bulk of FFN, their averages have been considered.

Here is a better estimate, statistically not different than the first, but more exact for the human eye: 3,213,946.

What does that say to you? FanFiction.Net is only 54%-53% (without/with 0.987 coefficient) of what it appears to the layman, with the remaining 46%-47% being deleted content. As such, you may take it that every second story is destined to be deleted, and out of every two stories You post only one will survive (statistically).

What about the second method? Aside from these real numbers taken in raw, the research includes a sample of 1100 randomly generated story IDs with a range [1;6085534], which allows the research to continue with case study at a 3% error margin and a 95,34% confidence level. The survivability estimate taken from the sample size is 55%, which is within the 3% acceptable error and statistically identical to 54%-53%, received with the help of raw data. For future studies, this means our method of sampling follows the general population's characteristics.

In conclusion, there are 3,213,946 stories on FanFiction.Net at the time of our study, and nearly half of all stories posted will sooner or later disappear. How soon? Come back later to find out!

Should you require additional data, requests can be made in the comments, emailed to Lord Kelvin or posted in the Literate Union forum. The list used in our sample can be found here:
http://www.usbupload.com/23228_FFNstatsdatadoc.usb
http://www.usbupload.com/23227_samplelinksFFNdoc.usb

Tuesday 29 June 2010

Welcome!

This blog has been created to store all the data Lord Kelvin and other curious people banded under the FFN Research flag have or are collecting about FanFiction.Net. Expect analysis, various facts and queries in every informative post.

Finding hard data related to fandom and fan fiction has been...difficult as of late. Anything available online was either inaccurate, obsolete or cost $600 for a peek. This was unacceptable, so we took matters into our own hands. Our purpose is to become a reputable basis for every worthwhile query. By fans. For fans. We all hope our efforts and studies are going to inspire you, dear readers, to join this cause.

If you have any requests, post them in comments below. Alternatively, you may send feedback and ideas to Lord Kelvin.