Classifying the Products/Items for Online Shopping By Analysing Textual Reviews Based On Social Sentiment Attributes

Satish Kumar Avilineni, Madala Guru Brahmam


In late years, we have seen a flourish of audit sites. It shows an incredible chance to share our perspectives for different items we purchase. However, we confront a data over-burdening issue. The most effective method to mine significant data from audits to comprehend a client's inclinations and make a precise suggestion is vital. Customary recommender frameworks (RS) think about a few elements, for example, client's buy records, item classification, and geographic area. In this work, we propose an assumption based rating forecast strategy (RPS) to enhance expectation exactness in prescribed frameworks. Right off the bat, we propose a social client wistful estimation approach and compute every client's slant on things/items. Besides, we consider a client's own nostalgic qualities as well as mull over relational wistful influence. At that point, we think about item notoriety, which can be deduced by the wistful conveyances of a client set that reflect clients' extensive assessment. Finally, we intertwine three variables—client notion similitude, relational wistful influence, and thing's notoriety comparability—into our recommender framework to make an exact rating expectation. We lead an execution assessment of the three wistful factors on a genuine dataset gathered from Yelp.

Full Text:


Copyright (c) 2018 Edupedia Publications Pvt Ltd

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


All published Articles are Open Access at 

Paper submission: