Kerry Raymond: "A really exciting result would be the ability to predict stock price movements from WP editing behaviour!"
I am actually funded by a project where we are trying that. We have looked a bit on Twitter sentiment (like everyone else is doing), but now also do Wikipedia sentiment analysis for companies.
You see an example here for the Lundbeck pharmaceutical company:
http://rb.imm.dtu.dk/base/c/Lundbeck
The plots are for Wikipedia sentiment through time, Twitter sentiment through time and stock price (plots not aligned temporally).
Lundbeck had bad publicity last year. One of their drugs was, without their acceptance, used for executions in United States. There is a drop in Twitter sentiment in regard to that issue -- and also a slight drop in Wikipedia sentiment. It is unclear to me whether the stock price movement is related to that media issue.
I have not completed the analysis. But you see some further companies here http://rb.imm.dtu.dk/base/c/ Mostly it is only the Swedish and Danish companies I have run through the sentiment analysis.
Finn Årup Nielsen
I think that's a brilliant idea. The point I'd like to make is that a combination of data from different channels, would work the best. While for instance, Twitter could be considered as the massive public view on some product, Wikipedia data would be seen as an input about more professional individuals with more accurate information. I think this is the place to point to a recent paper by Osborne et al: Bieber no more: *First Story Detection* using *Twitter* and *Wikipedia*http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CDQQFjAA&url=http%3A%2F%2Fresearch.microsoft.com%2Fen-us%2Fpeople%2Fmilads%2Fosbornetaia2012.pdf&ei=k4GbUKeJH5HPsgaM0YHQCw&usg=AFQjCNHdxw5DgY9-9OMRVx6l5znyknbhgQ, where they have used such combination to detect "First Stories".
On Thu, Nov 8, 2012 at 10:06 AM, Finn Årup Nielsen fn@imm.dtu.dk wrote:
Kerry Raymond: "A really exciting result would be the ability to predict stock price movements from WP editing behaviour!"
I am actually funded by a project where we are trying that. We have looked a bit on Twitter sentiment (like everyone else is doing), but now also do Wikipedia sentiment analysis for companies.
You see an example here for the Lundbeck pharmaceutical company:
http://rb.imm.dtu.dk/base/c/**Lundbeckhttp://rb.imm.dtu.dk/base/c/Lundbeck
The plots are for Wikipedia sentiment through time, Twitter sentiment through time and stock price (plots not aligned temporally).
Lundbeck had bad publicity last year. One of their drugs was, without their acceptance, used for executions in United States. There is a drop in Twitter sentiment in regard to that issue -- and also a slight drop in Wikipedia sentiment. It is unclear to me whether the stock price movement is related to that media issue.
I have not completed the analysis. But you see some further companies here http://rb.imm.dtu.dk/base/c/ Mostly it is only the Swedish and Danish companies I have run through the sentiment analysis.
Finn Årup Nielsen
______________________________**_________________ Wiki-research-l mailing list Wiki-research-l@lists.**wikimedia.orgWiki-research-l@lists.wikimedia.org https://lists.wikimedia.org/**mailman/listinfo/wiki-**research-lhttps://lists.wikimedia.org/mailman/listinfo/wiki-research-l
Using Wikipedia for predicting stock market is being done from some time ago.
Obviously, the more stream data you have (Wikipedia, Twitter, Facebook, ...), the more info you can extract and attempt to "predict" some changes in the stock.
Anyway, although Wikipedia license allows reusing the info for any case, I think that this is a sad case. The effects of stock markets include famines (speculation of food prices) and other basic goods. A death machine.
A more humane approach for this "big data" is what Google did with their searches. For example, detecting the spread of flu when people search "headache" and similar terms.
2012/11/8 Taha Yasseri taha.yaseri@gmail.com
I think that's a brilliant idea. The point I'd like to make is that a combination of data from different channels, would work the best. While for instance, Twitter could be considered as the massive public view on some product, Wikipedia data would be seen as an input about more professional individuals with more accurate information. I think this is the place to point to a recent paper by Osborne et al: Bieber no more: *First Story Detection* using *Twitter* and *Wikipedia*http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CDQQFjAA&url=http%3A%2F%2Fresearch.microsoft.com%2Fen-us%2Fpeople%2Fmilads%2Fosbornetaia2012.pdf&ei=k4GbUKeJH5HPsgaM0YHQCw&usg=AFQjCNHdxw5DgY9-9OMRVx6l5znyknbhgQ, where they have used such combination to detect "First Stories".
On Thu, Nov 8, 2012 at 10:06 AM, Finn Årup Nielsen fn@imm.dtu.dk wrote:
Kerry Raymond: "A really exciting result would be the ability to predict stock price movements from WP editing behaviour!"
I am actually funded by a project where we are trying that. We have looked a bit on Twitter sentiment (like everyone else is doing), but now also do Wikipedia sentiment analysis for companies.
You see an example here for the Lundbeck pharmaceutical company:
http://rb.imm.dtu.dk/base/c/**Lundbeckhttp://rb.imm.dtu.dk/base/c/Lundbeck
The plots are for Wikipedia sentiment through time, Twitter sentiment through time and stock price (plots not aligned temporally).
Lundbeck had bad publicity last year. One of their drugs was, without their acceptance, used for executions in United States. There is a drop in Twitter sentiment in regard to that issue -- and also a slight drop in Wikipedia sentiment. It is unclear to me whether the stock price movement is related to that media issue.
I have not completed the analysis. But you see some further companies here http://rb.imm.dtu.dk/base/c/ Mostly it is only the Swedish and Danish companies I have run through the sentiment analysis.
Finn Årup Nielsen
______________________________**_________________ Wiki-research-l mailing list Wiki-research-l@lists.**wikimedia.orgWiki-research-l@lists.wikimedia.org https://lists.wikimedia.org/**mailman/listinfo/wiki-**research-lhttps://lists.wikimedia.org/mailman/listinfo/wiki-research-l
-- .t
Wiki-research-l mailing list Wiki-research-l@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/wiki-research-l
On 08-11-2012 11:16, emijrp wrote:
Using Wikipedia for predicting stock market is being done from some time ago.
Are there any public information on that? When I search Google Scholar for Wikipedia and "Stock price" I see a lot of papers but noone relevant on the first pages.
Obviously, the more stream data you have (Wikipedia, Twitter, Facebook, ...), the more info you can extract and attempt to "predict" some changes in the stock.
Anyway, although Wikipedia license allows reusing the info for any case, I think that this is a sad case. The effects of stock markets include famines (speculation of food prices) and other basic goods. A death machine.
A more humane approach for this "big data" is what Google did with their searches. For example, detecting the spread of flu when people search "headache" and similar terms.
This has already been done to some degree with Wikipedia. There is this marvelous wiki with wiki research ;-), which lists the Laurent/Vickers paper:
http://wikipapers.referata.com/wiki/Seeking_health_information_online:_does_...
On Wikilit we do not seem to have a good category for trend/event detection. We list this paper under Currency and Ranking and popularity among other categories:
http://wikilit.referata.com/wiki/Seeking_health_information_online:_does_Wik... and it is summarized under Health Information Source in our review: http://ssrn.com/abstract=2021326
In my Wikipedia Review I have a section called "Trend spotting and prediction" (pages 18-19) http://www2.imm.dtu.dk/pubdb/views/edoc_download.php/6012/pdf/imm6012.pdf
Laurent/Vickers is the only real paper I have included so far. (For some reason Nunes' Wikitrends and Summers' Wikichanges webservices do not work for me at the moment). Taha Yasseri's pointers to "Bieber no more" and his own paper seems to be number 2nd and 3rd.
I do too feel that it is a bit of a sad case with commercialization of Wikipedia. I do see COI edits in relation to the companies. In the project I am involved in we are interested in corporate social responsibility. I guess a focus on CSR instead of stock price would be a less sad case.
/Finn
2012/11/8 Taha Yasseri <taha.yaseri@gmail.com mailto:taha.yaseri@gmail.com>
I think that's a brilliant idea. The point I'd like to make is that a combination of data from different channels, would work the best. While for instance, Twitter could be considered as the massive public view on some product, Wikipedia data would be seen as an input about more professional individuals with more accurate information. I think this is the place to point to a recent paper by Osborne et al: Bieber no more: /First Story Detection/ using /Twitter/ and /Wikipedia/ <http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CDQQFjAA&url=http%3A%2F%2Fresearch.microsoft.com%2Fen-us%2Fpeople%2Fmilads%2Fosbornetaia2012.pdf&ei=k4GbUKeJH5HPsgaM0YHQCw&usg=AFQjCNHdxw5DgY9-9OMRVx6l5znyknbhgQ>, where they have used such combination to detect "First Stories". On Thu, Nov 8, 2012 at 10:06 AM, Finn Årup Nielsen <fn@imm.dtu.dk <mailto:fn@imm.dtu.dk>> wrote: Kerry Raymond: "A really exciting result would be the ability to predict stock price movements from WP editing behaviour!" I am actually funded by a project where we are trying that. We have looked a bit on Twitter sentiment (like everyone else is doing), but now also do Wikipedia sentiment analysis for companies. You see an example here for the Lundbeck pharmaceutical company: http://rb.imm.dtu.dk/base/c/__Lundbeck <http://rb.imm.dtu.dk/base/c/Lundbeck> The plots are for Wikipedia sentiment through time, Twitter sentiment through time and stock price (plots not aligned temporally). Lundbeck had bad publicity last year. One of their drugs was, without their acceptance, used for executions in United States. There is a drop in Twitter sentiment in regard to that issue -- and also a slight drop in Wikipedia sentiment. It is unclear to me whether the stock price movement is related to that media issue. I have not completed the analysis. But you see some further companies here http://rb.imm.dtu.dk/base/c/ Mostly it is only the Swedish and Danish companies I have run through the sentiment analysis. Finn Årup Nielsen _________________________________________________ Wiki-research-l mailing list Wiki-research-l@lists.__wikimedia.org <mailto:Wiki-research-l@lists.wikimedia.org> https://lists.wikimedia.org/__mailman/listinfo/wiki-__research-l <https://lists.wikimedia.org/mailman/listinfo/wiki-research-l> -- .t _______________________________________________ Wiki-research-l mailing list Wiki-research-l@lists.wikimedia.org <mailto:Wiki-research-l@lists.wikimedia.org> https://lists.wikimedia.org/mailman/listinfo/wiki-research-l-- Emilio J. Rodríguez-Posada http://LibreFind.org - The wiki search engine
Wiki-research-l mailing list Wiki-research-l@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/wiki-research-l
2012/11/8 Finn Årup Nielsen fn@imm.dtu.dk
On 08-11-2012 11:16, emijrp wrote:
Using Wikipedia for predicting stock market is being done from some time ago.
Are there any public information on that? When I search Google Scholar for Wikipedia and "Stock price" I see a lot of papers but noone relevant on the first pages.
I don't remember where but I read about that, perhaps in Slashdot, HackerNews... It was a company that had a copy of Wikipedia database and many more data streams, and they use it to "predict" changes in the stock market. Very few details were given.
wiki-research-l@lists.wikimedia.org