Causal Reconstruction of Sentiment Signals from Sparse News Data

TL;DR

This paper introduces a causal reconstruction pipeline for transforming sparse, noisy news sentiment data into stable, reliable temporal sentiment signals, validated against stock prices, emphasizing the importance of reconstruction over classifier accuracy.

Contribution

The paper presents a modular, three-stage causal signal reconstruction method for sentiment analysis from sparse news data, including a novel label-free evaluation framework and empirical validation against stock prices.

Findings

Reconstructed sentiment signals show a consistent three-week lead over stock prices.

The pipeline improves signal stability and robustness to data sparsity and redundancy.

Stable sentiment indicators are achievable through careful reconstruction, not just better classifiers.

Abstract

Sentiment signals derived from sparse news are commonly used in financial analysis and technology monitoring, yet transforming raw article-level observations into reliable temporal series remains a largely unsolved engineering problem. Rather than treating this as a classification challenge, we propose to frame it as a causal signal reconstruction problem: given probabilistic sentiment outputs from a fixed classifier, recover a stable latent sentiment series that is robust to the structural pathologies of news data such as sparsity, redundancy, and classifier uncertainty. We present a modular three-stage pipeline that (i) aggregates article-level scores onto a regular temporal grid with uncertainty-aware and redundancy-aware weights, (ii) fills coverage gaps through strictly causal projection rules, and (iii) applies causal smoothing to reduce residual noise. Because ground-truth longitudinal sentiment labels are typically unavailable, we introduce a label-free evaluation framework based on signal stability diagnostics, information preservation lag proxies, and counterfactual tests for causality compliance and redundancy robustness. As a secondary external check, we evaluate the consistency of reconstructed signals against stock-price data for a multi-firm dataset of AI-related news titles (November 2024 to February 2026). The key empirical finding is a three-week lead lag pattern between reconstructed sentiment and price that persists across all tested pipeline configurations and aggregation regimes, a structural regularity more informative than any single correlation coefficient. Overall, the results support the view that stable, deployable sentiment indicators require careful reconstruction, not only better classifiers.