Mining sentiment tendencies and summaries from consumer reviews
- PDF / 1,338,501 Bytes
- 29 Pages / 439.37 x 666.142 pts Page_size
- 91 Downloads / 196 Views
Mining sentiment tendencies and summaries from consumer reviews Wen‑Jie Ye1 · Anthony J. T. Lee1 Received: 18 January 2020 / Revised: 30 July 2020 / Accepted: 28 September 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Consumer reviews are an invaluable aid for businesses in obtaining consumers’ feed‑ back to facilitate their marketing campaigns. However, the rapidly increasing num‑ ber of consumer reviews makes it difficult for businesses to obtain a comprehensive view of consumer opinions about their products, especially about the highlighted product features. This study presents a framework to provide an understanding of how consumers’ feedback changes over time and what concerns consumers most. The framework presented here contributes to consumer review analysis in three ways. First, a novel model is proposed to extract the feature words that are semanti‑ cally relevant to each highlighted product feature. Second, consumers’ feedback on each highlighted product feature is converted into a sentiment tendency graph, which may reflect how the feedback changes over time. Third, consumers’ feedback is also summarized, which may reveal what consumers appreciate and what concerns them most. The experimental results show that the proposed model can effectively extract the feature words for each highlighted feature of the product. Moreover, both senti‑ ment tendency graphs and summaries could complement each other and provide a more detailed picture for consumers and manufacturers. Keywords Opinion mining · Sentiment analysis · Summarization · Latent Dirichlet allocation model · Bidirectional encoder representations from transformers model
* Anthony J. T. Lee [email protected] Wen‑Jie Ye [email protected] 1
Department of Information Management, National Taiwan University, No. 1, Sec. 4, Roosevelt Road, Taipei 10617, Taiwan, ROC
13
Vol.:(0123456789)
W.-J. Ye, A. J. T. Lee
1 Introduction Online consumer reviews play an increasingly important role in consumers’ purchase decisions. A recent study from Pew Research indicates that about eightin-ten Americans are now online shoppers. Of these online shoppers, 82% consult online reviews when buying something for the first time.1 Online consumer reviews are replete with useful information for consumers and manufacturers. They reduce information asymmetry between manufacturers and consumers, and create value for both sides. Consumers can read reviews to compare the strengths and weaknesses of products while manufacturers can obtain immediate feedback to improve their products. Manufacturers often highlight certain features of their new products to attract consumers. This is more common when manufacturers advertise a new product in a series to highlight the features that distinguish the product from others in the series. However, the highlighted features may or may not meet consumers’ needs, and con‑ sumers’ attitudes toward the highlighted features may change over time. Sentiment analysis may help us know better about how cons
Data Loading...
