Session: CIE-24-02 - AMS-CAPPD-SEIKEM: Artificial Intelligence and Machine Learning in Design and Manufacturing

Paper Number: 90108

90108 - Aspect-Sentiment-Guided Opinion Summarization for User Need Elicitation From Online Reviews 

Extracting and analyzing informative user opinion from large-scale online reviews is a key success factor in product design processes. However, user reviews are naturally unstructured, noisy, and verbose. Recent advances in abstractive text summrization provide an unprecedented opportunity to systematically generate summaries of user opinions to facilitate need finding for designers. Yet, two main gaps in the state-of-the-art opinion summarization methods limit their applicability to the product design domain. First is the lack of capabilities to guide the generative process with respect to various product aspects and user sentiments (e.g., polarity, subjectivity), and the second gap is the lack of annotated training datasets for supervised learning. This paper tackles these gaps by (1) devising an efficient and scalable methodology for abstractive opinion summarization from online reviews guided by aspects terms and sentiment polarities, and (2) automatically generating a reusable synthetic training dataset that captures various degrees of granularity and polarity. The methodology contributes a multi-instance pooling model with aspect and sentiment information integrated (MAS), a synthetic data assembled using the results of the MAS model, and a fine-tuned pretrained sequence-to-sequence model ``T5'' for summary generation. Numerical experiments are conducted on a large dataset scraped from a major e-commerce retail store for sneakers to demonstrate the performance, feasibility, and potentials of the developed methodology. Several directions are provided for future exploration in the area of automated opinion summarization for user-centered product design.

Presenting Author: Yi Han Northeastern University

Presenting Author Biography: Yi Han is a PhD student in the Department of Mechanical and Industrial Engineering at Northeastern University. His research focus is the artificial intelligence techniques and their application in the product design process, including user need finding, sentiment analysis, text mining, and other techniques that could benefit designers in the product design process.

Authors:

Yi Han Northeastern University
Mohsen Moghaddam Northeastern University
Meet Tusharbhai Suthar Purdue University
Gaurav Nanda Purdue University