InsightNet: Structured Insight Mining from Customer Feedback

TL;DR

InsightNet is an innovative machine learning framework that automatically extracts structured, hierarchical insights from customer reviews, improving accuracy and generalization over existing methods.

Contribution

It introduces a semi-supervised, multi-level taxonomy and a multi-task LLM-based architecture for detailed insight extraction from raw reviews.

Findings

Achieves an F1 score of 0.85 in multi-label topic classification.

Outperforms previous methods by 11% in F1-score.

Generalizes well to unseen aspects and suggests new topics.

Abstract

We propose InsightNet, a novel approach for the automated extraction of structured insights from customer reviews. Our end-to-end machine learning framework is designed to overcome the limitations of current solutions, including the absence of structure for identified topics, non-standard aspect names, and lack of abundant training data. The proposed solution builds a semi-supervised multi-level taxonomy from raw reviews, a semantic similarity heuristic approach to generate labelled data and employs a multi-task insight extraction architecture by fine-tuning an LLM. InsightNet identifies granular actionable topics with customer sentiments and verbatim for each topic. Evaluations on real-world customer review data show that InsightNet performs better than existing solutions in terms of structure, hierarchy and completeness. We empirically demonstrate that InsightNet outperforms the current state-of-the-art methods in multi-label topic classification, achieving an F1 score of 0.85, which is an improvement of 11% F1-score over the previous best results. Additionally, InsightNet generalises well for unseen aspects and suggests new topics to be added to the taxonomy.