Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

1.4%2.8%4.2%5.6% · Dec 201919922001200920182026
48 results for sentiment transfer

Detects non-linear causality between social media sentiment and cryptocurrency prices.

problem Detecting causality between non-linear time series data.
method Use of transfer entropy to measure information transfer, validating against synthetic data, and applying significance tests.
result Significant non-linear causality detected, orders of magnitude greater than linear causality.

Study compares sentiment spillover networks from news and social media in tech companies.

problem Understanding how sentiment information flows between companies through news and social media.
method Network-based transfer entropy method to measure and compare sentiment spillover.
result News shows stronger information flow among tech companies after COVID-19.

Improved sentiment analysis in Korean finance using masked PLMs.

problem Fine-grained sentiment analysis in non-English finance literature is lacking due to limited annotated data.
method Developed KorFinASC dataset and applied TGT-Masking to PLMs to remove non-stationary knowledge.
result Improved classification accuracy by 22.63% on KorFinASC.

Paper tackles ASC with coarse-to-fine task transfer for AT-level sentiment classification.

problem Small AT-level corpora and limited data for fine-grained AT task.
method Coarse-to-fine task transfer using MGAN with Coarse2Fine attention and contrastive feature alignment.
result MGAN improves ASC performance on AT-level sentiment classification.

Images have become one of the most popular types of media through which users convey their emotions within online social networks. Although vast amount of research is devoted to sentiment analysis of textual data, there has been very limited work that focuses on analyzing sentiment of image data. In this work, we propo…

2014-11-21abs ↗pdf ↗

This paper compares deep transfer learning with classical ML in low-shot text classification.

problem Low-shot text classification with limited labeled data.
method Comparison of BERT and top classical ML approaches on a sentiment classification task.
result BERT outperforms classical ML by 9.7% on average with 100 labeled examples per class.

Method selects task-specific neurons for unsupervised transfer learning.

problem Challenges in fine-tuning large language models for specific tasks.
method Selects important neurons for a specific classification task and extends to multi-source transfer learning.
result Higher similarity between task-specific fingerprints leads to better transferability.

Paper tackles domain invariant sentiment classification using weak supervision.

problem Learning a sentiment classification model that adapts to any target domain.
method Two-stage training procedure with weakly supervised datasets.
result Transfer learning with weak supervision achieves performance close to supervised training.

A new method improves cross-domain sentiment analysis by learning weighted domain-invariant representations.

problem Label distribution changes across domains harm domain adaptation in DIRL.
method Proposes WDIRL, a modification to DIRL that learns weighted domain-invariant representations.
result Empirical studies show the effectiveness of WDIRL in cross-domain sentiment analysis.

Study shows publicly available news impacts financial markets.

problem Impact of publicly available news on financial markets.
method Extracted news from Common Crawl, identified relevant companies, used sentiment analysis and information theory.
result Publicly available news has significant impact on financial markets.

Generative model evaluates text emotion intensity, outperforming classification.

problem Limitations of discrete emotion classification in applied domains.
method Fine-tuning generative language models to output continuous emotion intensity scores.
result Generative model outperforms classification baselines and reveals generalization capabilities.

AlphaMLDigger predicts excess returns in fluctuating markets.

problem Mining effective information for investment decisions in a volatile market.
method Two-phase approach using deep NLP for sentiment analysis and ensemble ML models.
result Ensemble models achieve 0.984 accuracy, significantly outperforming baseline.

This paper improves sentence-level sentiment analysis of financial news.

problem Blurred insights into individual sentences' sentiment in financial news.
method Distributed text representations and multi-instance learning.
result Superior predictive performance of up to 69.90%.

GIRNet tackles multi-tasking with mixed domain sequences, improving sentiment and tagging tasks.

problem Labeling sequences with mixed domain data and position-specific inference.
method Unified position-sensitive multi-task RNN architecture with gated state sequences from auxiliary data.
result GIRNet achieves new state-of-the-art performance in sentiment classification, POS tagging, and target position-sensitive annotation.

Paper introduces metrics to assess and control nuisance factors in sentiment analysis.

problem Challenges in learning invariant representations for sentiment analysis due to entangled nuisance factors.
method Developed two generalization metrics and a data filtering approach to control nuisance factors.
result Simple text classification baseline can be badly affected by product ID in sentiment analysis.

Quantformer uses transformer to predict stock returns, outperforming traditional strategies.

problem Predicting stock returns in a dynamic financial market.
method Transfer learning from sentiment analysis to build investment factors using a transformer-based neural network.
result Quantformer outperforms other 100-factor-based quantitative strategies in predicting stock trends.

Survey of LLMs in finance tasks, highlighting progress and challenges.

problem Transforming financial practices with advanced LLMs.
method Exploration of various financial tasks, categorization, and analysis of methodologies.
result Unlocking novel opportunities for financial applications with LLMs.

Study finds investor sentiment has a significant positive relationship with stock returns in Moroccan and Tunisian markets.

problem Investor sentiment and stock returns relationship in Moroccan and Tunisian markets.
method Used indirect measures of investor sentiment (SENT and ARMS) and Granger causality tests.
result Sentiment has a significant positive relationship with stock returns, but not the other way around.

A new teacher-class network method compresses DNNs by distributing knowledge to multiple student networks.

problem Overwhelming size of Deep Neural Networks (DNNs).
method Single teacher with multiple student networks, transferring knowledge to each student.
result The combined knowledge of the class of students achieves better performance and reduces parameters.

News sentiment in U.S. economic newspapers has become more persistent over 45 years.

problem Understanding the temporal dynamics of U.S. economic news sentiment over time.
method Daily economic news sentiment index from 1980-2025, analyzed using sentiment indexes.
result News sentiment states have become more persistent, with longer residence times in optimistic or pessimistic regimes.

Study uses Granger causality to show investor sentiment influences stock prices.

problem Understanding the relationship between investor sentiment and stock market movements.
method Applied Granger causality to analyze the relationship between close price index and sentiment score.
result Sentiment analysis shows a positive correlation with stock price movements.

Can textual data be compressed intelligently without losing accuracy in evaluating sentiment? In this study, we propose a novel evolutionary compression algorithm, PARSEC (PARts-of-Speech for sEntiment Compression), which makes use of Parts-of-Speech tags to compress text in a way that sacrifices minimal classification…

2017-09-20abs ↗pdf ↗

Investor sentiment improves model accuracy but complexity doesn't always boost predictive power.

problem Determining the optimal complexity of investor sentiment measures in asset pricing models.
method Comprehensive review of 71 papers from 2000-2021, analyzing various sentiment measures and models.
result Higher complexity of sentiment measures does not necessarily improve predictive power.

The ability to identify sentiment in text, referred to as sentiment analysis, is one which is natural to adult humans. This task is, however, not one which a computer can perform by default. Identifying sentiments in an automated, algorithmic manner will be a useful capability for business and research in their search …

2018-04-05abs ↗pdf ↗

Model quantifies market sentiment using news data.

problem Quantifying high-frequency market sentiment for economists.
method Support vector machine classifiers for sentiment analysis; stochastic volatility model for joint evolution.
result News sentiment raises the threshold of volatility reversion.

TSPRA integrates topics, sentiment, and user preference for better online review prediction and analysis.

problem Improving online review prediction and sentiment analysis accuracy.
method HDP-based model combining topics, sentiment, and user preference.
result Outperforms state-of-the-art model FLAME in rating prediction and sentiment analysis.

Enhanced portfolio selection using sentiment data and LSTM.

problem Improving portfolio selection through sentiment analysis and price prediction.
method Semantic Attention Model for sentiment prediction, LSTM for price prediction, mean-variance strategy for portfolio optimization.
result Sentiment-aware portfolio strategies outperform non-sentiment aware models on average.

Sentiment analysis of DAX40 stocks improves performance by 5.38% annually.

problem Creating a more responsive stock market index using sentiment analysis.
method Extract sentiment from news articles, adjust index weights based on sentiment, compare performance to existing indices.
result Sentiment index outperforms DAX40 by 7.51% annually, adjusted for costs.

Study uses sentiment analysis to predict implied volatility surface, improving prediction accuracy.

problem Improving prediction accuracy of implied volatility surface.
method Constructed daily high-frequency sentiment data, used VAR method, deep learning (BERT, LSTM), FFT, EMD for sentiment decomposition.
result High-frequency sentiment correlates with ATM options' implied volatility, low-frequency with DOTM options.

Combining deep neural networks with structured logic rules is desirable to harness flexibility and reduce uninterpretability of the neural models. We propose a general framework capable of enhancing various types of neural networks (e.g., CNNs and RNNs) with declarative first-order logic rules. Specifically, we develop…

2016-03-21abs ↗pdf ↗

ArSentD-LEV dataset improves sentiment analysis in Levantine Arabic tweets.

problem Challenges in sentiment analysis of Arabic tweets, especially Levantine dialect.
method Created a dataset of 4,000 Levantine Arabic tweets with detailed sentiment and topic annotations.
result Improved performance of sentiment classifiers with detailed annotations.