MétaCan
Menu
Back to cohort
Record W4416159922 · doi:10.4236/ajibm.2025.1511087

Research on the Nonlinear Impact of Investor Sentiment on Stock Returns Based on Deep Learning and Text Mining

2025· article· W4416159922 on OpenAlexaff
Fangchen Liu

Bibliographic record

VenueAmerican Journal of Industrial and Business Management · 2025
Typearticle
Language
FieldDecision Sciences
TopicStock Market Forecasting Methods
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsSentiment analysisStock marketStock (firearms)Deep learningsortEmpirical researchInvestment decisionsSupport vector machine

Abstract

fetched live from OpenAlex

This paper focuses on the nonlinear correlation between investor sentiment and stock returns and conducts in-depth research with the aid of deep learning and text mining techniques. First of all, sort out the relevant theoretical cornerstones, covering behavioral finance, market efficiency theory and herd effect theory, to provide theoretical support for the research. Secondly, analyze and study the data context, including the characteristics of text data and stock market data, as well as the necessity of integrated correlation analysis. In terms of extracting investor sentiment indicators, compare the advantages and disadvantages of the sentiment dictionary method, the machine learning method and the deep learning method. Subsequently, an in-depth exploration was conducted on the manifestations, theoretical explanations and implications for investment decisions of the nonlinear impact of investor sentiment on stock returns. Empirical results show that investor sentiment has a significant nonlinear impact on stock returns, and the degree of influence varies among different emotional states. This research provides investors with more accurate sentiment analysis tools to help them predict the trend of the stock market more scientifically and optimize investment decisions.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.021
metaresearch head score (Gemma)0.010
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.961
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0210.010
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0030.006
Science and technology studies0.0010.001
Scholarly communication0.0010.000
Open science0.0010.001
Research integrity0.0000.002
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.175
GPT teacher head0.443
Teacher spread0.268 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designOther design
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueAmerican Journal of Industrial and Business ManagementSame topicStock Market Forecasting MethodsFrench-language works237,207