Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Text Mining South Park

kaylinwalker.com

Post reply on HN
Print view View original

41–50 of 53 posts

Re: Text Mining South Park

#41

Post by nanis »

vsbuffalo wrote: post #35
nanis wrote: post #12

I was in the process of reading this when I thought to check who this person is. Of course, by that time the site had failed, so I haven't read the whole thing yet. But, it seems to me that the author is falling in to a trap many an unwary data "scientist" falls by not understanding the discipline of Statistics. When one has the entire population data (i.e. a census), rather than a sample, there is no point in carryi…

You're treating this sample-is-the-population issue as if it's resolved in the statistics literature. It is not. Gelman has written on this [1][2], as the issue comes up in political science data frequently. As Gelman points out, 50 states are not a sample of states—it's the entire population. Similarly, the Correlates of War [3] data is every militarized international dispute between 1816-2007 that fits certain crit…

As an economist, I am also aware of the logical contortions we have to go through to be able to run regressions on historical data (i.e. pretty much all of economic data). None of this applies here. The data generating process consists of the minds of the writers.

For your reasoning to be applicable here, you have to put together a model of the data generating process from which you can derive a proper model that allows inference. What exactly are the assumptions on P( word_i | character_j ) that make it compatible with these particular tests' assumptions?

Re: Text Mining South Park

#42

Post by make3 »

nanis wrote: post #12

I was in the process of reading this when I thought to check who this person is. Of course, by that time the site had failed, so I haven't read the whole thing yet. But, it seems to me that the author is falling in to a trap many an unwary data "scientist" falls by not understanding the discipline of Statistics. When one has the entire population data (i.e. a census), rather than a sample, there is no point in carryi…

Would the fact that he/she does not have the future text in his sample/population and that he uses this dataset as a sample of all the southparks to be ever written (in a prediction mode) make this make sense

Re: Text Mining South Park

#43

Post by Dowwie »

nanis wrote: post #34
JoeAltmaier wrote: post #29

Earlier quoted context omitted.

By that definition: a complete sample ?

No. > A complete sample is a set of objects from a parent population that includes ALL such objects that satisfy a set of well-defined selection criteria.[3] For example, a complete sample of Australian men taller than 2m would consist of a list of every Australian male taller than 2m. But it wouldn't include German males, or tall Australian females, or people shorter than 2m ... So, the entire set of all words spoke…

Your argument is sound

this seems fitting, though https://giphy.com/gifs/week-media-person-RL0xU1daTlMoE

Re: Text Mining South Park

#44

Post by ZoF »

nanis wrote: post #15
ZoF wrote: post #14

Earlier quoted context omitted.

This implies there aren't future episodes upon which this type of statistical analysis could be applied. This also strongly implies you think the author is a 'budding data scientist' out of his/her league. This is very much a 'sample' given the context that South Park is still releasing new episodes. FYI all elitist 'statisticians' ...

If one is trying to figure out what characters will say in future episodes based on their speech in previous episodes, then you are in a prediction context, not significance testing context. As far as I can tell, there are a lot of people out of their leagues going around with the title "data scientist". This is not a sample. This is a census at this point in time. The fact that there will be another population tomor…

You're the worst kind of intelligent person tbh.

Why be a nitpicking pedant when it is clear this is intended as a throwaway exercise whose only application is predictive...?

Re: Text Mining South Park

#45

Post by toupeira »

nanis wrote: post #15
ZoF wrote: post #14

Earlier quoted context omitted.

This implies there aren't future episodes upon which this type of statistical analysis could be applied. This also strongly implies you think the author is a 'budding data scientist' out of his/her league. This is very much a 'sample' given the context that South Park is still releasing new episodes. FYI all elitist 'statisticians' ...

If one is trying to figure out what characters will say in future episodes based on their speech in previous episodes, then you are in a prediction context, not significance testing context. As far as I can tell, there are a lot of people out of their leagues going around with the title "data scientist". This is not a sample. This is a census at this point in time. The fact that there will be another population tomor…

You're the one calling people "data scientists", OP didn't even use the word "science" anywhere in the article.

Re: Text Mining South Park

#46

Post by platz »

Dowwie wrote: post #43
nanis wrote: post #34

Earlier quoted context omitted.

No. > A complete sample is a set of objects from a parent population that includes ALL such objects that satisfy a set of well-defined selection criteria.[3] For example, a complete sample of Australian men taller than 2m would consist of a list of every Australian male taller than 2m. But it wouldn't include German males, or tall Australian females, or people shorter than 2m ... So, the entire set of all words spoke…

Your argument is sound this seems fitting, though https://giphy.com/gifs/week-media-person-RL0xU1daTlMoE

It's necessary because others refuse to listen and change their position, even when presented with evidence they are wrong.

Re: Text Mining South Park

#47

Post by walkerkq »

nanis wrote: post #12

I was in the process of reading this when I thought to check who this person is. Of course, by that time the site had failed, so I haven't read the whole thing yet. But, it seems to me that the author is falling in to a trap many an unwary data "scientist" falls by not understanding the discipline of Statistics. When one has the entire population data (i.e. a census), rather than a sample, there is no point in carryi…

Hi, I'm the author. I appreciate the time you've taken to read and provide constructive criticism of my work. Here's my full write up (on GitHub, so it should continue to work): https://github.com/walkerkq/textmining_southpark/blob/master...

I was working under the assumption that we do not know ALL the words since the show's been renewed through 2019. This covers the first 18 seasons.

Additionally, the counting up their most frequent words produced results with very little semantic meaning - things like "just" and "dont" - which can be seen in this (really boring) wordcloud: https://github.com/walkerkq/textmining_southpark/blob/master...

Looking into the log likelihood of each word for each speaker produced results that were much more intuitive and carried more meaning, like ppod said below: I think the idea is that what we are really trying to measure is something unobservable like the underlying nature of the character or the writers' tendencies to give characters certain ways of speaking.

Re: Text Mining South Park

#48

Post by bobadams5 »

bobadams5 wrote: post #22
minimaxir wrote: post #21

Earlier quoted context omitted.

I took a look at the code in the author's GitHub repository. The data sources are CSVs in this repository: https://github.com/BobAdamsEE/SouthParkData/ Looks like all the data is preprocessed, with everyone mostly having only 1 line. (Actually, it appears the line you note in 10-3 is broken!) You can make an argument that the script isn't processed correctly, but that's beyond the scope of the analysis, although a no…

It's my repository. I'll look at how the python script handles flashback events later today. Thanks for the feedback!

It appears that there are two issues that affect small parts of the captured datasets:

1) Colored character names are not handled properly. I looked for tags, not tags.

2) Character names that start with a lower case character are not handled. This may have to do with other episodes using lower case prefixed table headers for stage directions, I have to double check.

Re: Text Mining South Park

#49

Post by flashman »

agentgt wrote: post #5

I wonder how the results would change if it was based not on words but rather by lines (not string lines but actor lines in conversation). Its also funny how Stan talks more than Kyle given the show now has a recurring joke that makes fun of Kyle's long educational dialogues.

It would definitely change. For instance I'd expect Kyle's words-per-sentence (or at least his 90th percentile sentence length) to be higher than Stan's, due to his speeches.

Re: Text Mining South Park

#50

Post by nanis »

walkerkq wrote: post #47
nanis wrote: post #12

I was in the process of reading this when I thought to check who this person is. Of course, by that time the site had failed, so I haven't read the whole thing yet. But, it seems to me that the author is falling in to a trap many an unwary data "scientist" falls by not understanding the discipline of Statistics. When one has the entire population data (i.e. a census), rather than a sample, there is no point in carryi…

Hi, I'm the author. I appreciate the time you've taken to read and provide constructive criticism of my work. Here's my full write up (on GitHub, so it should continue to work): https://github.com/walkerkq/textmining_southpark/blob/master... I was working under the assumption that we do not know ALL the words since the show's been renewed through 2019. This covers the first 18 seasons. Additionally, the counting up t…

The point I am making is simple: You can calculate whatever you want to calculate, but there is no room for statistical testing because you do not have a probability sample, and, no sampling variation.

Yes, there will be future episodes, but you are not claiming that you are predicting what these characters will say in those future episodes (in which case your whole setup is rather inappropriate).

Also, I suggest you think very hard about this statement:

> The log likelihood value of 101.7 is significant far beyond even the 0.01% level, so we can reject the null hypothesis that Cartman and the remaining text are one and the same.

Even if the statistical test you employed were appropriate, this is not the conclusion you draw from it.

Also, are you confusing p = 0.01 with 1% or did you really choose p = 0.00001 as the significance level for your test?

Post reply on HN