Review-Based Recommender System for Hedonic and Utilitarian Products in IoT Framework
- Publisher:
- Springer Nature
- Publication Type:
- Conference Proceeding
- Citation:
- Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, 2022, 421 LNICST, pp. 221-232
- Issue Date:
- 2022-01-01
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
978-3-030-95987-6_16.pdf | Published version | 544.34 kB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
With the tremendous increase in product alternatives these days, many businesses rely heavily on recommender systems to limit the number of options they display to their customers on the front end. Many companies use the collaborative filtering algorithm and provide suggestions based on other consumers’ choices, like the active user. However, this approach faces a cold start problem and is not suitable for one-time transactions. Thus, this research aims to create a recommender system that uses online customer reviews in the IoT framework to match the attributes of a product important to the shopper. The algorithm makes recommendations by first identifying the product’s features essential to a customer. It then performs aspect-based sentiment analysis to identify those features in customer reviews and give them a sentiment score. Each customer review is weighted based on its creditably. As the impact of the recommender systems varies with the product type, an experimental study will be carried out to study the effect of the proposed algorithm differs with hedonic and utilitarian products.
Please use this identifier to cite or link to this item: