ABSApp: A Portable Weakly-Supervised Aspect-Based Sentiment Extraction System

TL;DR

ABSApp is a portable, interpretable system for aspect-based sentiment extraction that operates without labeled data, enabling rapid, domain-specific sentiment analysis through user interaction and lexicon editing.

Contribution

It introduces a weakly-supervised, user-friendly system that generates and refines aspect and opinion lexicons for domain-specific sentiment analysis without labeled training data.

Findings

Successfully applied in movie review analysis

Effective in convention impact analysis

Operates without labeled datasets

Abstract

We present ABSApp, a portable system for weakly-supervised aspect-based sentiment extraction. The system is interpretable and user friendly and does not require labeled training data, hence can be rapidly and cost-effectively used across different domains in applied setups. The system flow includes three stages: First, it generates domain-specific aspect and opinion lexicons based on an unlabeled dataset; second, it enables the user to view and edit those lexicons (weak supervision); and finally, it enables the user to select an unlabeled target dataset from the same domain, classify it, and generate an aspect-based sentiment report. ABSApp has been successfully used in a number of real-life use cases, among them movie review analysis and convention impact analysis.