Sentiment aggregation of targeted features by capturing their dependencies: Making sense from customer reviews |
| |
| Institution: | 1. Centre for Computational Intelligence, De Montfort University, Leicester, UK;2. Bissett School of Business, Mount Royal University, Calgary, Canada;3. Iwate Prefectural University, Takizawa, Iwate, Japan;1. Department of Computer Science, South Asian University, New Delhi, India;2. Department of Computer Science & Engineering, APJAKTU, Lucknow, India;3. Department of Computer Science, Banaras Hindu University, Varanasi, India |
| |
| Abstract: | Ideation is an important phase in the new product development process at which product designers innovate and select novel ideas that can be added as features to an existing product. One way to find novel ideas is to transfer uncommon features of products of other domains and integrate them into the product to be improved. However, before incorporating such targeted features into the product, they need to be evaluated against the customers’ acceptance in social media using sentiment aggregation tools. Despite the many studies in sentiment analysis, mapping the customers’ opinions towards both high-level and technical features of a product extracted from social media to their best corresponding component in that product is still a challenge. Furthermore, none of the existing approaches ascertains the sentiment value of a targeted feature by capturing its dependencies on other features. In this paper, to address these drawbacks, we propose the sentiment aggregation framework for targeted features (SA-TF). SA-TF determines the sentiment of a targeted feature by assisting product designers in the tasks of mapping the features discussed in the reviews to the right product components, sentiment aggregation and considering feature dependencies to determine their polarity. The superiority of the different phases of SA-TF is demonstrated with experiments and comparing it with an existing approach. |
| |
| Keywords: | New product development Ideation Sentiment aggregation Product tree Feature’s interaction Decision recommendation |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
