{"paper_id":"2311.06273","title":"Potential of ChatGPT in predicting stock market trends based on Twitter Sentiment Analysis","authors":["Ummara Mumtaz","Summaya Mumtaz"],"paper_date":"2023-10-13","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2311.06273v1","page_url":"https://thequant.space/flowcharts/potential-of-chatgpt-in-predicting-stock-market-trends-based/","scores":{"empirical_rigor":4,"math_complexity":3,"quadrant":"Philosophers"},"proposes":{"status":"available","statement":"The paper proposes using ChatGPT with zero-shot learning on Twitter sentiment to predict stock market trends for Microsoft and Google.","quote":"In this study, we explore the potential of using ChatGPT in predicting stock market trends solely based on Twitter sentiment analysis and by employing the zero-shot learning strategy.","summary":"The rise of ChatGPT has brought a notable shift to the AI sector, with its exceptional conversational skills and deep grasp of language. Recognizing its value across different areas, our study investigates ChatGPT’s capacity to predict stock market movements using only social media tweets and…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Minimal data cleaning (only URL removal) is sufficient for sentiment analysis.","type":"data","stated":"explicit","quote":"We performed minimal data cleaning and only removed URL present in the tweets."},{"assumption":"Tweets mentioning Microsoft or Google contain relevant sentiment for those stocks.","type":"data","stated":"explicit","quote":"Tweets were specifically sought that mentioned or related to three distinct terms: 'ChatGPT', 'Microsoft', and 'Google'."},{"assumption":"ChatGPT can predict stock trends without fine‑tuning, using zero‑shot learning.","type":"model","stated":"explicit","quote":"Considering ChatGPT was not exclusively fine-tuned for stock market predictions and employing a zero-shot learning strategy, its performance is notably superior to a model making random predictions."},{"assumption":"The relationship between tweet sentiment and next‑day stock returns is stable over the sample period.","type":"market","stated":"implied","quote":"Our findings highlight a positive link between ChatGPT's evaluations and the following days stock results for both tech companies."},{"assumption":"Trading can be evaluated purely on prediction accuracy without accounting for transaction costs.","type":"execution","stated":"implied","quote":"The results indicate that ChatGPT achieved an accuracy of 70% for Microsoft and 63.88% for Google."}]},"datasets":{"status":"available","items":[{"name":"500k ChatGPT-related Tweets Jan-Mar 2023","provider":"Kaggle","kind":"alternative","access":"public","period":"2023-01-04 to 2023-03-29","universe":"Tweets containing 'gpt', 'ChatGPT', 'Microsoft', or 'Google'","quote":"We utilized a publicly available dataset at Kaggle named “500k ChatGPT-related Tweets Jan-Mar 2023”","known_id":"kaggle"},{"name":"NASDAQ stock price data for Google and Microsoft","provider":"NASDAQ website","kind":"market-prices","access":"public","period":"2023-01-04 to 2023-02-28","universe":"Google and Microsoft stocks","quote":"Stock performance data for Google and Microsoft was procured from the NASDAQ website."}],"known":[{"id":"twitter","name":"Twitter / X","provider":"X Corp.","kind":"text-news","access":"public","quote":"Furthermore, it's crucial to emphasize that the analysis was conducted using a restrained set of tweets, hinting that a more exhaustive data set from Twitter or other social platforms might yield even better insights.","mentions":17,"used_in":1},{"id":"kaggle","name":"Kaggle","provider":"Kaggle","kind":"other","access":"public","quote":"Data Collection & Pre-processing : We utilized a publicly available dataset at Kaggle named “500k ChatGPT-related Tweets Jan-Mar 2023”[1] for this analysis.","mentions":1,"used_in":1}],"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":"no","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"ChatGPT correctly predicted Microsoft’s daily stock trend on 26 out of 37 days, yielding 70% accuracy.","kind":"predictive-accuracy","quote":"For Microsoft, out of a 37-day period, ChatGPT's predictions aligned with the actual outcomes on 26 occasions. Thus, getting an accuracy of 70% for Microsoft stock market trend prediction."},{"finding":"ChatGPT correctly predicted Google’s daily stock trend on 23 out of 36 days, yielding roughly 63.88% accuracy.","kind":"predictive-accuracy","quote":"out of a 36-day timeframe, the model made accurate forecasts on 23 days, resulting in an accuracy of roughly 63.88%."},{"finding":"A positive link was observed between ChatGPT’s sentiment evaluations and the next‑day stock results for both companies.","kind":"performance","quote":"Our findings highlight a positive link between ChatGPT's evaluations and the following days stock results for both tech companies."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":24,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"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":"2026-11-14T16:34:42Z"},"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/"}