{"paper_id":"2404.03792","title":"Social Media Emotions and Market Behavior","authors":["Domonkos F. Vamossy"],"paper_date":"2024-04-04","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2404.03792v1","page_url":"https://thequant.space/flowcharts/social-media-emotions-and-market-behavior/","scores":{"empirical_rigor":6,"math_complexity":3.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper uses the open‑source EmTract emotion model to show that firm‑specific investor emotions from social media behave like lab experiments and can forecast daily asset price movements.","quote":"My findings reveal that firm-specific investor emotions behave similarly to lab experiments and can forecast daily asset price movements.","summary":"I explore the relationship between investor emotions expressed on social media and asset prices. The field has seen a proliferation of models aimed at extracting firm-level sentiment from social media data, though the behavior of these models often remains uncertain. Against this backdrop, my study…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Traders exhibiting loss aversion tend to avoid firms with smaller market capitalizations.","type":"model","stated":"explicit","quote":"To test these, I operate under two key assumptions: first, that traders exhibiting loss aversion tend to steer clear of firms with smaller market capitalizations, possibly due to perceived higher risks; and second, that there is a relationship between trading volume and cash holdings, where increased trading activity s"},{"assumption":"There is a relationship between trading volume and cash holdings, with higher volume implying lower cash reserves.","type":"model","stated":"explicit","quote":"To test these, I operate under two key assumptions: first, that traders exhibiting loss aversion tend to steer clear of firms with smaller market capitalizations, possibly due to perceived higher risks; and second, that there is a relationship between trading volume and cash holdings, where increased trading activity s"}]},"datasets":{"status":"available","items":[{"name":"StockTwits messages","provider":"StockTwits","kind":"alternative","access":"public","period":"January 1st 2010 to September 30th 2021","universe":"active, common ordinary shares traded on US exchanges","quote":"Sample starts January 1st 2010 and runs till September 30th 2021. I filter out stocks for which the security status (SECSTAT is “I”) is inactive and restrict my sample to common ordinary shares (TPCI is “0”) traded on US exchanges (EXCHG is 11, 12, 14, or 17).","known_id":"stocktwits"},{"name":"CRSP/Compustat sample","provider":"CRSP/Compustat","kind":"fundamentals","access":"commercial","period":"January 1st 2010 to September 30th 2021","universe":"active, common ordinary shares traded on US exchanges","quote":"dataset with a parallel sample from CRSP/Compustat for the same period, adhering to identical sample criteria (i.e., active, common ordinary shares on U.S. exchanges).","known_id":"crsp"}],"known":[{"id":"stocktwits","name":"StockTwits","provider":"StockTwits","kind":"text-news","access":"public","quote":"2 Data 2.1 Social Media Data (StockTwits) My dataset on investor emotions is sourced from StockTwits, established in 2008 as a plat-form for investors to exchange opinions on stocks.","mentions":17,"used_in":3},{"id":"twitter","name":"Twitter / X","provider":"X Corp.","kind":"text-news","access":"public","quote":"4.3.1 Alternative Classification I use alternative emotion variables using a model trained on Twitter emotion metadata collected by other researchers.","mentions":10,"used_in":3},{"id":"compustat","name":"Compustat","provider":"S&P Global","kind":"fundamentals","access":"commercial","quote":"Variables related to stock prices were sourced from the merged CRSP/COMPUSTAT file, while short interest data came from Compustat’s Supplemental Short Interest File.","mentions":6,"used_in":2},{"id":"crsp","name":"CRSP","provider":"Center for Research in Security Prices","kind":"market-prices","access":"commercial","quote":"Variables related to stock prices were sourced from the merged CRSP/COMPUSTAT file, while short interest data came from Compustat’s Supplemental Short Interest File.","mentions":6,"used_in":2}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"n/a","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"Investor emotions extracted from social media forecast daily stock price fluctuations.","kind":"predictive-accuracy","quote":"My findings reveal that firm-specific investor emotions behave similarly to lab experiments and can forecast daily asset price movements."},{"finding":"The predictive impact of emotions is larger when liquidity is lower or short interest is higher.","kind":"performance","quote":"These impacts are larger when liquidity is lower or short interest is higher."},{"finding":"Sadness has a persistent negative influence on subsequent returns, while a one‑dimensional valence metric is insignificant.","kind":"statistical","quote":"My findings on the persistent influence of sadness on subsequent returns, along with the insignificance of the one-dimensional valence metric, underscores the importance of dissecting emotional states."},{"finding":"Investor emotions are significant predictors of daily stock price movements, especially with greater short interest and lower liquidity.","kind":"predictive-accuracy","quote":"investor emotions are significant predictors of daily stock price movements, with their influence being more pronounced when accompanied by greater short interest, and lower levels of liquidity."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[{"paper":{"paper_id":"2309.00136","title":"Predicting Financial Market Trends using Time Series Analysis and Natural Language Processing","paper_date":"2023-08-31","authors":["Ali Asgarov"],"empirical_rigor":4,"page_url":"https://thequant.space/flowcharts/predicting-financial-market-trends-using-time-series-analysi/"},"question":"Do investor emotions extracted from social media predict daily stock price fluctuations?","this_paper_finding":"Investor emotions extracted from social media forecast daily stock price fluctuations.","other_paper_finding":"A robust association was observed between tweet emotions (positivity, negativity, subjectivity) and stock price fluctuations.","other_paper_quote":"Our study has revealed a robust association between the emotions conveyed in tweets and fluctuations in stock prices.","note":"Both findings report a robust association between tweet/emotion metrics and daily stock price changes; B’s result supports A’s observation.","confidence":0.876},{"paper":{"paper_id":"2309.00136","title":"Predicting Financial Market Trends using Time Series Analysis and Natural Language Processing","paper_date":"2023-08-31","authors":["Ali Asgarov"],"empirical_rigor":4,"page_url":"https://thequant.space/flowcharts/predicting-financial-market-trends-using-time-series-analysi/"},"question":"Do tweet‑derived investor emotions predict daily stock price movements?","this_paper_finding":"Investor emotions are significant predictors of daily stock price movements, especially with greater short interest and lower liquidity.","other_paper_finding":"A robust association was observed between tweet emotions (positivity, negativity, subjectivity) and stock price fluctuations.","other_paper_quote":"Our study has revealed a robust association between the emotions conveyed in tweets and fluctuations in stock prices.","note":"Both findings report a significant association between social‑media emotions and stock price changes, confirming emotions as predictors.","confidence":0.823}],"contradicts":[{"paper":{"paper_id":"2305.16632","title":"Causality between investor sentiment and the shares return on the Moroccan and Tunisian financial markets","paper_date":"2023-05-26","authors":["Chniguir Mounira","Henchiri Jamel Eddine"],"empirical_rigor":7,"page_url":"https://thequant.space/flowcharts/causality-between-investor-sentiment-and-the-shares-return-o/"},"question":"Do investor sentiment or emotions affect daily stock returns?","this_paper_finding":"Investor emotions are significant predictors of daily stock price movements, especially with greater short interest and lower liquidity.","other_paper_finding":"Profitability (stock returns) causes investor sentiment, not the reverse, for both markets.","other_paper_quote":"The results of the Granger causality test between stock return and investor sentiment show us that profitability causes investor sentiment and not the other way around for the two financial markets studied.","note":"A finds returns cause sentiment (no reverse effect), B finds sentiment predicts returns; opposite conclusions across markets.","confidence":0.529}],"qualifies":[],"compared_with":17,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T18:11:47Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}