Forex trading and Twitter: spam, bots, and reputation manipulation. Mozetič, I., Gabrovšek, P., & Novak, P. K. Working Paper MIS2: Misinformation and Misbehavior Mining on the Web, 2018. abstract bibtex Currency trading (Forex) is the largest world market in terms of volume. We analyze trading and tweeting about the EUR-USD currency pair over a period of three years. First, a large number of tweets were manually labeled, and a Twitter stance classification model is constructed. The model then classifies all the tweets by the trading stance signal: buy, hold, or sell (EUR vs. USD). The Twitter stance is compared to the actual currency rates by applying the event study methodology, well-known in financial economics. It turns out that there are large differences in Twitter stance distribution and potential trading returns between the four groups of Twitter users: trading robots, spammers, trading companies, and individual traders. Additionally, we observe attempts of reputation manipulation by post festum removal of tweets with poor predictions, and deleting/reposting of identical tweets to increase the visibility without tainting one's Twitter timeline.
@article{mozetic2018bforex,
abstract = {Currency trading (Forex) is the largest world market in terms of volume. We analyze trading and tweeting about the EUR-USD currency pair over a period of three years. First, a large number of tweets were manually labeled, and a Twitter stance classification model is constructed. The model then classifies all the tweets by the trading stance signal: buy, hold, or sell (EUR vs. USD). The Twitter stance is compared to the actual currency rates by applying the event study methodology, well-known in financial economics. It turns out that there are large differences in Twitter stance distribution and potential trading returns between the four groups of Twitter users: trading robots, spammers, trading companies, and individual traders. Additionally, we observe attempts of reputation manipulation by post festum removal of tweets with poor predictions, and deleting/reposting of identical tweets to increase the visibility without tainting one's Twitter timeline.},
archivePrefix = {arXiv},
arxivId = {1804.02233},
author = {Mozeti{\v{c}}, Igor and Gabrov{\v{s}}ek, Peter and Novak, Petra Kralj},
eprint = {1804.02233},
file = {::},
journal = {Working Paper MIS2: Misinformation and Misbehavior Mining on the Web},
keywords = {DOLFINS{\_}T3.1,DOLFINS{\_}WP3,DOLFINS{\_}working{\_}paper},
mendeley-tags = {DOLFINS{\_}T3.1,DOLFINS{\_}WP3,DOLFINS{\_}working{\_}paper},
title = {{Forex trading and Twitter: spam, bots, and reputation manipulation}},
year = {2018}
}
Downloads: 0
{"_id":"aXJWQwHL7k67pr8sw","bibbaseid":"mozeti-gabrovek-novak-forextradingandtwitterspambotsandreputationmanipulation-2018","downloads":0,"creationDate":"2018-04-01T15:33:00.858Z","title":"Forex trading and Twitter: spam, bots, and reputation manipulation","author_short":["Mozetič, I.","Gabrovšek, P.","Novak, P. K."],"year":2018,"bibtype":"article","biburl":"https://simpolproject.eu/download/Bibliography/DOLFINS2018.06.11v1.bib","bibdata":{"bibtype":"article","type":"article","abstract":"Currency trading (Forex) is the largest world market in terms of volume. We analyze trading and tweeting about the EUR-USD currency pair over a period of three years. First, a large number of tweets were manually labeled, and a Twitter stance classification model is constructed. The model then classifies all the tweets by the trading stance signal: buy, hold, or sell (EUR vs. USD). The Twitter stance is compared to the actual currency rates by applying the event study methodology, well-known in financial economics. It turns out that there are large differences in Twitter stance distribution and potential trading returns between the four groups of Twitter users: trading robots, spammers, trading companies, and individual traders. Additionally, we observe attempts of reputation manipulation by post festum removal of tweets with poor predictions, and deleting/reposting of identical tweets to increase the visibility without tainting one's Twitter timeline.","archiveprefix":"arXiv","arxivid":"1804.02233","author":[{"propositions":[],"lastnames":["Mozetič"],"firstnames":["Igor"],"suffixes":[]},{"propositions":[],"lastnames":["Gabrovšek"],"firstnames":["Peter"],"suffixes":[]},{"propositions":[],"lastnames":["Novak"],"firstnames":["Petra","Kralj"],"suffixes":[]}],"eprint":"1804.02233","file":"::","journal":"Working Paper MIS2: Misinformation and Misbehavior Mining on the Web","keywords":"DOLFINS_T3.1,DOLFINS_WP3,DOLFINS_working_paper","mendeley-tags":"DOLFINS_T3.1,DOLFINS_WP3,DOLFINS_working_paper","title":"Forex trading and Twitter: spam, bots, and reputation manipulation","year":"2018","bibtex":"@article{mozetic2018bforex,\nabstract = {Currency trading (Forex) is the largest world market in terms of volume. We analyze trading and tweeting about the EUR-USD currency pair over a period of three years. First, a large number of tweets were manually labeled, and a Twitter stance classification model is constructed. The model then classifies all the tweets by the trading stance signal: buy, hold, or sell (EUR vs. USD). The Twitter stance is compared to the actual currency rates by applying the event study methodology, well-known in financial economics. It turns out that there are large differences in Twitter stance distribution and potential trading returns between the four groups of Twitter users: trading robots, spammers, trading companies, and individual traders. Additionally, we observe attempts of reputation manipulation by post festum removal of tweets with poor predictions, and deleting/reposting of identical tweets to increase the visibility without tainting one's Twitter timeline.},\narchivePrefix = {arXiv},\narxivId = {1804.02233},\nauthor = {Mozeti{\\v{c}}, Igor and Gabrov{\\v{s}}ek, Peter and Novak, Petra Kralj},\neprint = {1804.02233},\nfile = {::},\njournal = {Working Paper MIS2: Misinformation and Misbehavior Mining on the Web},\nkeywords = {DOLFINS{\\_}T3.1,DOLFINS{\\_}WP3,DOLFINS{\\_}working{\\_}paper},\nmendeley-tags = {DOLFINS{\\_}T3.1,DOLFINS{\\_}WP3,DOLFINS{\\_}working{\\_}paper},\ntitle = {{Forex trading and Twitter: spam, bots, and reputation manipulation}},\nyear = {2018}\n}\n","author_short":["Mozetič, I.","Gabrovšek, P.","Novak, P. K."],"key":"mozetic2018bforex","id":"mozetic2018bforex","bibbaseid":"mozeti-gabrovek-novak-forextradingandtwitterspambotsandreputationmanipulation-2018","role":"author","urls":{},"keyword":["DOLFINS_T3.1","DOLFINS_WP3","DOLFINS_working_paper"],"downloads":0},"search_terms":["forex","trading","twitter","spam","bots","reputation","manipulation","mozetič","gabrovšek","novak"],"keywords":["forex","twitter sentiment/stance","deleting/reposting tweets","event study","reputation manipulation","dolfins_t3.1","dolfins_wp3","dolfins_working_paper"],"authorIDs":[],"dataSources":["JBCT4AXyeopWLaLMW"]}