{"paper_id":"2309.11979","title":"Stock Market Sentiment Classification and Backtesting via Fine-tuned BERT","authors":["Jiashu Lou"],"paper_date":"2023-09-21","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2309.11979v1","page_url":"https://thequant.space/flowcharts/stock-market-sentiment-classification-and-backtesting-via-fi/","scores":{"empirical_rigor":6,"math_complexity":3,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a BERT-based sentiment analysis model for stock forum posts and uses its polarity signals in an automatic trading system.","quote":"paper uses the BERT model to perform sentiment analysis on the post titles, and uses the sentiment polarity values as trading signal factors, and develops an automatic trading system.","summary":"With the rapid development of big data and computing devices, low-latency automatic trading platforms based on real-time information acquisition have become the main components of the stock trading market, so the topic of quantitative trading has received widespread attention. And for non-strongly…","strategy":"Sentiment-enhanced Alpha191 model"},"assumptions":{"status":"available","items":[{"assumption":"A transaction fee of 0.5% is applied to each trade.","type":"execution","stated":"explicit","quote":"We set the transaction fee to 0.5%, and the initial capital to 100000."},{"assumption":"Each purchase must be held for at least 10 days before the next decision.","type":"execution","stated":"explicit","quote":"we also stipulate that each purchase must be held for at least 10 days before making the next decision"},{"assumption":"Buy signals are triggered when the predicted price change exceeds the 90th percentile of the test set; sell signals when below the 10th percentile.","type":"model","stated":"explicit","quote":"buy 1000 shares of the target when the prediction is greater than the 90th percentile of the test set, and sell 500 shares of the target when it is less than the 10th percentile."},{"assumption":"The THUCTC Chinese text classification dataset provides appropriate sentiment labels for fine‑tuning BERT.","type":"data","stated":"explicit","quote":"we have to rely on existing labeled datasets, here we use THUCTC Chinese text dataset."},{"assumption":"The 90,000 East Money comment titles from 2019‑01‑01 to 2020‑01‑01 are representative of market sentiment.","type":"data","stated":"explicit","quote":"about 90,000 comment titles from January 1, 2019 to January 1, 2020 are selected as experimental data."}]},"datasets":{"status":"available","items":[{"name":"THUCTC Chinese text dataset","provider":"Tsinghua University","kind":"text-news","access":"public","period":"2005-2011","universe":null,"quote":"THUCTC (THU Chinese Text Classification) is a Chinese text classification toolkit"},{"name":"East Money Stock BBS comment titles","provider":"East Money","kind":"alternative","access":"public","period":"2019-01-01 to 2020-01-01","universe":null,"quote":"about 90,000 comment titles from January 1, 2019 to January 1, 2020 are selected as experimental data."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":"equities","frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":false,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"partial","evidence_card":"yes","evidence_card_quoted":true},"conflict_kind":"graded","card_detail":"0.5% transaction fee per trade","card_quote":"We set the transaction fee to 0.5%, and the initial capital to 100000.","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Incorporating emotional factors increased the return rate by 73.8% compared to the baseline strategy.","kind":"performance","quote":"the incorporation of emotional factors increased the return rate by 73.8% compared to the baseline during the trading period"},{"finding":"The emotional‑enhanced model outperformed the original Alpha191 model by 32.41% in return rate.","kind":"performance","quote":"and by 32.41% compared to the original alpha191 model"},{"finding":"The fine‑tuned BERT model achieved performance improvements over the original BERT and baseline models.","kind":"predictive-accuracy","quote":"the fine‑tuned model has different degrees of performance improvement compared to the original model and the baseline model"}],"reported_performance":{"strategy":"Sentiment-enhanced Alpha191 model","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"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":"2026-11-14T18:21:50Z"},"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/"}