{"paper_id":"2306.02148","title":"The Role of Twitter in Cryptocurrency Pump-and-Dumps","authors":["David Ardia","Keven Bluteau"],"paper_date":"2023-06-03","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2306.02148v1","page_url":"https://thequant.space/flowcharts/the-role-of-twitter-in-cryptocurrency-pump-and-dumps/","scores":{"empirical_rigor":7.5,"math_complexity":3,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper investigates how Twitter promotion affects cryptocurrency pump‑and‑dump events by analyzing abnormal returns, trading volume and tweet activity.","quote":"We examine the influence of Twitter promotion on cryptocurrency pump-and-dump events.","summary":"We examine the influence of Twitter promotion on cryptocurrency pump-and-dump events. By analyzing abnormal returns, trading volume, and tweet activity, we uncover that Twitter effectively garners attention for pump-and-dump schemes, leading to notable effects on abnormal returns before the event.…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The analysis is limited to events on the Binance exchange using the Bitcoin trading pair.","type":"data","stated":"explicit","quote":"on events occurring on the Binance exchange using the Bitcoin (BTC) trading pair."},{"assumption":"Bitcoin is unlikely to be the primary target of pump‑and‑dump schemes.","type":"market","stated":"explicit","quote":"speculative asset, is unlikely to be the primary target of pump-and-dump schemes."},{"assumption":"Events involving highly popular coins (Dogecoin, Litecoin, Ethereum, Cardano) are excluded due to Twitter data‑collection limits.","type":"data","stated":"explicit","quote":"We exclude events related to Dogecoin, Litecoin, Ethereum, and Cardano, as their widespread popularity posed challenges in collecting data from Twitter."},{"assumption":"Abnormal tweet counts and abnormal returns are measured over one‑minute intervals.","type":"statistical","stated":"explicit","quote":"We gather volume and closing price data for cryptocurrencies at a one‑minute frequency..."}]},"datasets":{"status":"available","items":[{"name":"Pump‑and‑dump events database","provider":null,"kind":"alternative","access":"public","period":"2019‑02‑02 to 2022‑02‑02","universe":"1,160 pump‑and‑dump events on Binance","quote":"In total, our dataset comprises 1,160 pump-and-dump events."},{"name":"Telegram messages","provider":"Telegram API","kind":"text-news","access":"public","period":null,"universe":"messages from >100 pump‑and‑dump groups","quote":"The Telegram API, which is publicly accessible, facilitated downloading all messages from the groups or channels we had subscribed to or joined."},{"name":"Price and volume data","provider":"www.cryptoarchive.com.au (Binance API)","kind":"market-prices","access":"public","period":null,"universe":"minute‑level price and volume for Binance listed tokens","quote":"We gather volume and closing price data for cryptocurrencies at a one‑minute frequency from the website www.cryptoarchive.com.au.","known_id":"binance"},{"name":"Twitter data","provider":"Twitter API","kind":"text-news","access":"public","period":null,"universe":"tweets mentioning pump‑and‑dump events","quote":"Twitter is a microblogging social network enabling users to share posts with a maximum…","known_id":"twitter"}],"known":[{"id":"binance","name":"Binance","provider":"Binance","kind":"market-prices","access":"public","quote":"This data originates from the Binance API, ensuring that our analysis reflects the price and volume information available on the Binance trading platform. 3.3.","mentions":8,"used_in":4},{"id":"twitter","name":"Twitter / X","provider":"X Corp.","kind":"text-news","access":"public","quote":"We employ regression analysis to ascertain whether Twitter promotion effectively attracts additional participants to engage in the pump-and-dump event.","mentions":43,"used_in":3}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"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":"unclear","findings":[{"finding":"A higher abnormal number of tweets in the last 30 minutes before an event is positively and significantly associated with higher abnormal returns.","kind":"statistical","quote":"We observe a positive and statistically significant relationship between the abnormal number of tweets and abnormal returns."},{"finding":"The cumulative abnormal return before the event is significantly negatively related to the abnormal return during the dump phase, indicating larger pumps lead to larger dumps.","kind":"statistical","quote":"Our findings reveal a significant negative relationship between the cumulative abnormal return at and preceding the event and its equivalent during the dump window."},{"finding":"There is no significant relationship between pre‑event tweet volume and the cumulative abnormal return during the dump window, suggesting Twitter‑informed investors do not sell during the dump.","kind":"statistical","quote":"We do not observe a significant relationship between the abnormal number of tweets before the event and the cumulative abnormal return during the dump window."},{"finding":"Investors who receive information via Twitter sell later, causing a predominantly negative post‑dump abnormal return and larger losses compared to other participants.","kind":"performance","quote":"We observe a predominantly negative and statistically significant relationship between the post-dump abnormal return and the cumulative abnormal number of tweets before the event."},{"finding":"Twitter promotion is pivotal in attracting participants to pump‑and‑dump events, shaping participant behavior before, during, and after the event.","kind":"theoretical","quote":"Our regression analysis further confirms the influence of Twitter activity on abnormal returns before, during, and after the event, highlighting the significance of social media in shaping participant behavior."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[{"paper":{"paper_id":"2212.14689","title":"Cross-Domain Shopping and Stock Trend Analysis","paper_date":"2022-12-23","authors":["Aditya Pandey","Haseeba Fathiya","Nivedita Patel"],"empirical_rigor":3.5,"page_url":"https://thequant.space/flowcharts/cross-domain-shopping-and-stock-trend-analysis/"},"question":"Do spikes in tweet volume predict short‑term positive returns in stocks or cryptocurrencies?","this_paper_finding":"A higher abnormal number of tweets in the last 30 minutes before an event is positively and significantly associated with higher abnormal returns.","other_paper_finding":"An increase in the number of tweets precedes an increase in the number of \"Big Winning\" stocks by 0‑1 days.","other_paper_quote":"We also observe a general lag of 0-1 days, which suggests that an increase in the number of tweets is a reli-able indicator of an increase in the number of \"Big Winning\" stocks in the coming day or two.","note":"Both find a positive link: A shows tweet rise precedes more \"Big Winning\" stocks by 0‑1 days; B shows abnormal tweets in the last 30 min associate with higher abnormal returns.","confidence":0.554}],"contradicts":[],"qualifies":[],"compared_with":15,"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":"2026-11-14T18:26:15Z"},"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/"}