{"paper_id":"2401.05447","title":"Can ChatGPT Compute Trustworthy Sentiment Scores from Bloomberg Market Wraps?","authors":["Baptiste Lefort","Eric Benhamou","Jean-Jacques Ohana","David Saltiel","Beatrice Guez","Damien Challet"],"paper_date":"2024-01-09","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2401.05447v1","page_url":"https://thequant.space/flowcharts/can-chatgpt-compute-trustworthy-sentiment-scores-from-bloomb/","scores":{"empirical_rigor":6,"math_complexity":2.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a two-step ChatGPT‑based sentiment analysis method for Bloomberg market wrap news and an index to assess ChatGPT's sentiment scoring ability.","quote":"We designed a two-step ChatGPT based sentiment analysis extraction from Bloomberg markets wrap news.","summary":"We used a dataset of daily Bloomberg Financial Market Summaries from 2010 to 2023, reposted on large financial media, to determine how global news headlines may affect stock market movements using ChatGPT and a two-stage prompt approach. We document a statistically significant positive correlation…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Only news items longer than 600 characters and containing the keywords \"market(s) wrap\" are used.","type":"data","stated":"explicit","quote":"We ignored any text that is less than 600 characters long or any news summary that is not explicitly a market wrap by removing any text that does not contain the keywords \"market(s) wrap\"."},{"assumption":"The analysis uses the gpt‑4.0 version of ChatGPT for both prompts.","type":"model","stated":"explicit","quote":"For the two prompts, we used the gpt-4.0 version of ChatGPT."},{"assumption":"Sentiment scores are aggregated over a chosen duration d to form a cumulated sentiment score.","type":"statistical","stated":"explicit","quote":"Definition 4.2. Cumulated Sentiment Score:We defined a cumulative score as follows"},{"assumption":"Correlation analysis assumes linear relationships measured by Pearson and Spearman coefficients.","type":"statistical","stated":"explicit","quote":"Validation of this correlation pattern across multiple equity markets indicates its robustness"},{"assumption":"Equity returns are shifted in time to align with the cumulated sentiment score for correlation testing.","type":"market","stated":"explicit","quote":"The delay in market impact is instead associated with the temporal shift applied to the equity return data, which is examined against the cumulative sentiment scores."}]},"datasets":{"status":"available","items":[{"name":"Bloomberg Global Markets Wrap summaries","provider":"Bloomberg","kind":"text-news","access":"commercial","period":"2010-2023","universe":null,"quote":"We collected Bloomberg Global Markets Wrap summaries from 2010 to October 2023.","known_id":"bloomberg"}],"known":[{"id":"bloomberg","name":"Bloomberg","provider":"Bloomberg L.P.","kind":"market-prices","access":"commercial","quote":"Data collection We collected Bloomberg Global Markets Wrap sum-maries from 2010 to October 2023.","mentions":6,"used_in":4}],"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":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"A statistically significant positive correlation exists between the sentiment score and future equity market returns over short to medium horizons, which reverts to a negative correlation over longer horizons.","kind":"statistical","quote":"We document a statistically significant positive correlation between the sentiment score and future equity market returns over short to medium term, which reverts to a negative correlation over longer horizons."},{"finding":"The correlation pattern is robust across multiple equity markets and regions, as shown by high percentages of significant p‑values in US, Japan, Euro, UK and Emerging markets.","kind":"statistical","quote":"The results indicate a significant presence of the identified pattern across all markets, with an especially pronounced effect in the Japanese market (99%)."},{"finding":"An optimal horizon is identified that balances market reactivity to new information with the strength of the sentiment‑return correlation.","kind":"theoretical","quote":"Finally, we provide an estimate of the optimal horizon that strikes a balance between reactivity to new information and correlation."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":27,"citations":{"cited_by_in_corpus":2,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":2},"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":"2026-11-14T18:16:29Z"},"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/"}