Paper: arXiv 2510.15915

Authors: Tamoghna Mukherjee

Abstract

The stock market is heavily influenced by investor sentiment, which can drive buying or selling behavior. Sentiment analysis helps in gauging the overall sentiment of market participants towards a particular stock or the market as a whole. Positive sentiment often leads to increased buying activity and vice versa. Granger causality can be applied to ascertain whether changes in sentiment precede changes in stock prices.The study is focused on this aspect and tries to understand the relationship between close price index and sentiment score with the help of Granger causality inference. The study finds a positive response through hypothesis testing.

Complexity vs Empirical Score

  • Math Complexity: 3.0/10
  • Empirical Rigor: 5.0/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The paper employs Granger causality, a standard econometric method with moderate statistical rigor, but lacks advanced mathematical derivations or complex modeling. It demonstrates empirical rigor by applying the test to 5 years of real market data and reporting specific p-values for different lags, making it more practical than theoretical.

Research Flowchart

  flowchart TD
  A["Research Goal: Is there a Granger causal relationship<br>between investor sentiment and stock market movements?"]
  B["Data & Inputs: Stock Market Index (Close Prices)<br>Investor Sentiment Score"]
  C["Methodology: Preprocessing & Time Series Alignment<br>Sentiment Analysis & Granger Causality Test"]
  D["Computational Process: Construct Vector Autoregression Models<br>Perform F-test & Calculate Lag p-values"]
  E["Outcome: Rejection of Null Hypothesis<br>Significant Granger Causality Found"]
  F["Key Findings: Investor sentiment positively influences<br>future market movements. Sentiment precedes price action."]

  A --> B
  B --> C
  C --> D
  D --> E
  E --> F

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes to test whether sentiment scores Granger‑cause stock close prices using hypothesis testing.

Source sentence
The study is focused on this aspect and tries to understand the relationship between close price index and sentiment score with the help of Granger causality inference.

Assumes 2

  • There are enough observations in the time‑series data for a trustworthy analysis. statistical
    Source sentence
    We verify the time series data to make sure there are enough observations for a trustworthy analysis.
  • Sentiment can be quantified as a confidence score ranging from 0 to 1. data
    Source sentence
    A confidence score was derived that spans from 0 to 1, with 1 denoting extreme confidence and 0 denoting extreme uncertainty, in order to calculate the emotion score.

Data

  • Bombay Stock Exchange (BSE) intraday market transactions market-prices unknown
    May 2015 to May 2020
    Source sentence
    we applied the information in Bombay Stock Exchange (BSE) intraday market transactions
  • Indian financial domain news headlines text-news unknown
    May 2015 to May 2020
    Source sentence
    we have calculated the sentiment score of daily news headlines related to the Indian financial domain for a period of five years starting from May, 2015 to May, 2020.

Costs

Not applicable The paper reports no trading or execution result.

Finds 2

  • Sentiment score Granger‑causes the BSE close price (low p‑values, null hypothesis rejected). statistical
    Source sentence
    In this case since p value is low, hence null hypothesis is rejected. Alternate hypothesis is accepted.
  • Close price does not Granger‑cause sentiment score (high p‑values, null hypothesis accepted). statistical
    Source sentence
    In this case since p value is high, hence null hypothesis is accepted. Alternate hypothesis is rejected. Hence we can state that Sentiment Score influences Close Price.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 12 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.