Review-based analysis of clustering approaches in a recommendation system

Sabeena Yasmin Hera, Mohammad Amjad


Due to the explosion in data, it is now extremely challenging for a single individual to sift through all of the information and extract what they need. Therefore, information filtering technologies are required so that the relevant information may be discovered from the vast quantity of data now available online. Users can benefit from RSs since they streamline the process of identifying relevant content. User ratings are extremely important for making recommendations. Before, researchers relied on users' past ratings to make predictions about future ratings, but today people are paying more attention to user reviews because they contain so much useful information about the user's decision. The proposed approach employs the written testimonials in an effort to address the issue of doubt in the ratings' pasts. We conduct experimental evaluations of the proposed framework using two data sets. In this strategy, clustering methods are combined with NLP for prediction. It also compares the results produced by other methods, such as the K-mean, spectral, and hierarchical clustering algorithms, and draws conclusions about which approach is best for the provided recommendation use cases. In addition, we verify the superior performance of the suggested strategy compared to alternatives that do not use clustering.



  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

View IJICT Stats