{"paper_id":"2306.02136","title":"Financial sentiment analysis using FinBERT with application in predicting stock movement","authors":["Tingsong Jiang","Qingyun Zeng"],"paper_date":"2023-06-03","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2306.02136v3","page_url":"https://thequant.space/flowcharts/financial-sentiment-analysis-using-finbert-with-application/","scores":{"empirical_rigor":7.5,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a model that combines the financial domain‑adapted FinBERT transformer with an LSTM network to predict stock market movements using sentiment extracted from news.","quote":"We propose a model which takes advantage of Transformer based contextual language model for analyzing the sentiment in financial markets, and then using LSTM‑based deep learning model in the prediction of the exact movement of the financial market by the sentiment.","summary":"In this study, we integrate sentiment analysis within a financial framework by leveraging FinBERT, a fine-tuned BERT model specialized for financial text, to construct an advanced deep learning model based on Long Short-Term Memory (LSTM) networks. Our objective is to forecast financial market…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Financial sentiment from news, social media, etc. has strong correlations to market movements, based on the Efficient Market Hypothesis.","type":"market","stated":"explicit","quote":"Our basic hypothesis is that the financial sentiment by news, social media, etc. have strong correlations to the movement of financial markets (stock market, foreign exchange, bond, etc.). This hypothesis is based on Efficient Market Hypothesis (EMH), which states that share prices reflect all information."},{"assumption":"Statistical models like ARIMA do not capture the nonlinearity in financial data.","type":"model","stated":"explicit","quote":"Traditional statistical method such as ARIMA has been used widely in the modelling of financial markets. However, statistical models like ARIMA does not capture well the nonlinearity in the financial data."},{"assumption":"The relationship studied is correlation only; no causal analysis is performed.","type":"other","stated":"explicit","quote":"One thing need to be pointed our that, we are not doing casual analysis here, as market could influence news and news might also influence the market."},{"assumption":"Sentiment scores are aggregated daily per stock ticker by averaging probabilities of positive and negative classes.","type":"data","stated":"explicit","quote":"These probabilities were averaged daily per stock ticker, resulting in a daily aggregated sentiment score computed as: SentimentScore = P(positive) −P(negative)"},{"assumption":"Missing records are dropped and non‑trading days are handled by removing incomplete data.","type":"data","stated":"explicit","quote":"We handled missing values by dropping incomplete records."}]},"datasets":{"status":"available","items":[{"name":"Historical Financial News Archive","provider":"Kaggle.com","kind":"text-news","access":"public","period":"up to 2019 (12 years)","universe":"over 800 US companies","quote":"This dataset, publicly available on Kaggle.com, comprises news archives for over 800 US companies, spanning 12 years up to 2019.","known_id":"kaggle"},{"name":"Daily Financial News for 6000+ Stocks","provider":"Kaggle.com","kind":"text-news","access":"public","period":null,"universe":"6000+ stocks","quote":"Also sourced from Kaggle.com, this dataset offers a broader range of news items, albeit with less detailed information per entry (e.g., primarily headers).","known_id":"kaggle"},{"name":"Stock Market Data (price, volume, etc.)","provider":"yfinance API","kind":"market-prices","access":"public","period":null,"universe":"tickers identified in news datasets","quote":"We retrieve historical stock market data (e.g., open price, close price, percentage change) for the tickers identified in our news datasets using the yfinance API.","known_id":"yahoo-finance"},{"name":"FinBERT ('ProsusAI/finbert')","provider":"Hugging Face Model Hub","kind":"text-news","access":"public","period":null,"universe":null,"quote":"FinBERT (‘ProsusAI/finbert‘) obtained from the Hugging Face Model Hub."},{"name":"Base BERT uncased","provider":"Hugging Face Model Hub","kind":"text-news","access":"public","period":null,"universe":null,"quote":"We employ base BERT uncased and FinBERT (‘ProsusAI/finbert‘) obtained from the Hugging Face Model Hub."}],"known":[{"id":"kaggle","name":"Kaggle","provider":"Kaggle","kind":"other","access":"public","quote":"This dataset is joined with market data to facilitate both sentiment analysis and market movement prediction. • Daily Financial News for 6000+ Stocks (Supplemen-tary Textual Data): Also sourced from Kaggle.com, this dataset offers a broader range of news items, albeit with less detailed information per entry (e.g., primarily headers).","mentions":1,"used_in":1},{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"It serves to complement our primary news archive. • Stock Market Data: We retrieve historical stock market data (e.g., open price, close price, percentage change) for the tickers identified in our news datasets using the yfinance API.","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":"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":"FinBERT+LSTM achieves the lowest validation loss among all tested models.","kind":"performance","quote":"FINBERT + LSTM (PROPOSED) 9.1701E-05 3.1975E-04"},{"finding":"LSTM alone performs much better than ARIMA on the forecasting task.","kind":"predictive-accuracy","quote":"We find the the LSTM model in general perform much better than ARIMA model"},{"finding":"Sentiment analysis using FinBERT outperforms LSTM‑only models, and the combined FinBERT+LSTM model outperforms both.","kind":"predictive-accuracy","quote":"sentiment analysis using FinBERT out perform LSTM, whereras FinBERT combined with LSTM acheived the best performance."},{"finding":"ARIMA captures long‑run trends well but has higher MSE (0.00975) compared to the proposed model.","kind":"performance","quote":"ARIMA actually capture the long run trend well, whereas our model is able to fit the short run trend"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":46,"citations":{"cited_by_in_corpus":2,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":1,"mentions":0,"unclassified":1},"independent_papers":[{"paper":{"paper_id":"2411.12748","title":"FinBERT-BiLSTM: A Deep Learning Model for Predicting Volatile Cryptocurrency Market Prices Using Market Sentiment Dynamics","paper_date":"2024-11-02","authors":["Mabsur Fatin Bin Hossain","Lubna Zahan Lamia","Md Mahmudur Rahman","Md Mosaddek Khan"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/finbert-bilstm-a-deep-learning-model-for-predicting-volatil/"},"how":"discusses_findings","quote":"In both studies, FinBERT-LSTM gave the best results, outperforming the other models tested."}],"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":"2026-11-14T18:26:16Z"},"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/"}