Interpretable Word-Level Context-Based Sentiment Analysis
Authors:
- Chenyu YangCYChenyu Yang
- Eric LarsonELEric Larson
- Jing CaoJCJing Cao
Open Access
- 1 January 2026
- journal article
- Published by School of Statistics, Renmin University of China in Journal of Data Science
- p. 319-337
Abstract
We propose a fine-grained attention-based multiple instance classification (FAMIC) model for interpretable word-level sentiment analysis (SA) using only document-level sentiment labels. By operating at the word level, FAMIC enhances interpretability while maintaining competitive performance in document-level classification. The model generates interpretable outputs such as contextual weighting, word neutrality, and negation cues, offering insights into how context shapes sentiment and how the model arrives at its predictions. FAMIC is built on a straightforward yet effective architecture that combines a multiple instance classification framework with self-attention and positionally encoded self-attention blocks. This design enables the model to capture both local and global contextual dependencies, supporting nuanced sentiment interpretation. We evaluate FAMIC on two sentiment classification datasets and provide an extensive analysis of its interpretability and performance.Keywords
This publication has 17 references indexed in Scilit:
- Transformer-based deep learning models for the sentiment analysis of social media dataArray, 2022
- Using Neural Network Models for Wine Review ClassificationJournal of Wine Economics, 2022
- Opening the Black Box: The Promise and Limitations of Explainable Machine Learning in CardiologyCanadian Journal of Cardiology, 2022
- Knowledge-enabled BERT for aspect-based sentiment analysisKnowledge-Based Systems, 2021
- Context-aware positional representation for self-attention networksNeurocomputing, 2021
- Sentiment analysis on the impact of coronavirus in social life using the BERT modelSocial Network Analysis and Mining, 2021
- Multiple instance learning: A survey of problem characteristics and applicationsPattern Recognition, 2018
- Sentiment analysis algorithms and applications: A surveyAin Shams Engineering Journal, 2014
- Sentiment Analysis and Opinion Mining2012
- Solving the multiple instance problem with axis-parallel rectanglesArtificial Intelligence, 1997