{"paper_id":"2502.14897","title":"Market-Derived Financial Sentiment Analysis: Context-Aware Language Models for Crypto Forecasting","authors":["Hamid Moradi-Kamali","Mohammad-Hossein Rajabi-Ghozlou","Mahdi Ghazavi","Ali Soltani","Amirreza Sattarzadeh","Reza Entezari-Maleki"],"paper_date":"2025-02-17","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2502.14897v2","page_url":"https://thequant.space/flowcharts/market-derived-financial-sentiment-analysis-context-aware-l/","scores":{"empirical_rigor":6,"math_complexity":2.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a market-derived labeling approach for financial sentiment analysis and a context‑aware language model fine‑tuned on these labels to predict short‑term Bitcoin market movements.","quote":"To address these limitations, we propose a novel approach to FSA that focuses on measurable market reactions rather than inferred intentions.","summary":"Financial Sentiment Analysis (FSA) traditionally relies on human-annotated sentiment labels to infer investor sentiment and forecast market movements. However, inferring the potential market impact of words based on their human-perceived intentions is inherently challenging. We hypothesize that the…","strategy":"context-aware language model with TBL signal generation"},"assumptions":{"status":"available","items":[{"assumption":"Each tweet has a direct short‑term market impact that can be captured by the labeling scheme.","type":"market","stated":"explicit","quote":"Our approach assumes a direct short-term market impact for each tweet, which may oversimplify the intricate and often indirect relationship between social media activity and market movements."},{"assumption":"The model can learn to map tweet text to market movements without needing to model underlying intent.","type":"model","stated":"implied","quote":"By retaining the tweet’s representation, the model can identify nuanced relationships between specific words and their effect on market behavior, bridging the gap between textual sentiment and market outcomes."}]},"datasets":{"status":"available","items":[{"name":"Bitcoin Historical Events","provider":"Kaggle","kind":"text-news","access":"public","period":"2009-2024","universe":"significant Bitcoin market events","quote":"This dataset contains 227 significant Bitcoin market events from 2009 to 2024, focusing on benchmarking model performance during influential","known_id":"kaggle"},{"name":"Tweets","provider":"PreBit and Kaggle","kind":"alternative","access":"public","period":"2015-early 2023","universe":"Bitcoin‑related tweets","quote":"Tweet data from two sources, spanning 2015 to early 2023, was utilized. The first dataset","known_id":"kaggle"},{"name":"Technical Indicators (RSI, ROC)","provider":null,"kind":"market-prices","access":"public","period":"January 2015 to March 2023","universe":"OHLCV data for Bitcoin","quote":"The Relative Strength Index (RSI) and Rate of Change (ROC) are calculated from OHLCV"}],"known":[],"sample":{"start":null,"end":null,"market":"BTC/USDT","asset_class":"crypto","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Fine‑tuning the language model on market‑derived labels improves short‑term trend prediction accuracy by up to 11% over traditional sentiment benchmarks.","kind":"performance","quote":"A domain-specific language model was fine-tuned on these labels, achieving up to an 11% improvement in short-term trend prediction accuracy over traditional sentiment-based benchmarks."},{"finding":"The context‑aware language model attains 89.6% accuracy on a curated set of 227 impactful Bitcoin news events.","kind":"predictive-accuracy","quote":"the proposed context-aware language model demonstrated an accuracy of 89.6% on a curated dataset of 227 impactful Bitcoin-related news events with significant market impacts."},{"finding":"Aggregated trading signals from the model yield Sharpe ratios up to 5.07 in trending markets and 3.73 in neutral markets.","kind":"performance","quote":"Backtesting these signals across three distinct market regimes yielded robust Sharpe ratios of up to 5.07 in trending markets and 3.73 in neutral markets."},{"finding":"Using market‑derived labeling and prompt‑tuning raises the F1‑score from baseline to 80.3%, a 47% relative improvement.","kind":"predictive-accuracy","quote":"Fine-tuning language models with these market-derived labels improved the F1-score by 15.3%, and further integrating market context through prompt‑tuning boosted performance by a staggering 47%, reaching an F1-score of 80.3%."},{"finding":"The Majority TBL strategy achieves the highest Sharpe ratio of 5.07 in bullish markets and 4.70 in bearish markets, outperforming buy‑and‑hold benchmarks.","kind":"performance","quote":"Notably, the Majority TBL strategy achieved the highest Sharpe ratio in both the Bullish and Bearish markets, with a Sharpe ratio of 5.07 in the former and 4.70 in the latter."}],"reported_performance":{"strategy":"context-aware language model with TBL signal generation","sharpe":5.07,"sharpe_benchmark":3.12,"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":33,"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":true,"code_url":"https://github.com/hamidm21/Revisit_FSA","note":null},"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":"2026-11-14T17:45:31Z"},"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/"}