Sentiment-Aware Extractive and Abstractive Summarization for Unstructured Text Mining

TL;DR

This paper introduces a sentiment-aware summarization framework that enhances extractive and abstractive methods to better capture emotional nuances in noisy, user-generated texts, aiding decision-making in social media analysis.

Contribution

It presents a novel dual approach embedding sentiment signals into both extractive and abstractive summarization methods for unstructured social media data.

Findings

Improved sentiment preservation in summaries.

Enhanced thematic relevance and conciseness.

Better performance on noisy, informal texts.

Abstract

With the rapid growth of unstructured data from social media, reviews, and forums, text mining has become essential in Information Systems (IS) for extracting actionable insights. Summarization can condense fragmented, emotion-rich posts, but existing methods-optimized for structured news-struggle with noisy, informal content. Emotional cues are critical for IS tasks such as brand monitoring and market analysis, yet few studies integrate sentiment modeling into summarization of short user-generated texts. We propose a sentiment-aware framework extending extractive (TextRank) and abstractive (UniLM) approaches by embedding sentiment signals into ranking and generation processes. This dual design improves the capture of emotional nuances and thematic relevance, producing concise, sentiment-enriched summaries that enhance timely interventions and strategic decision-making in dynamic online environments.