IoT enabled machine learning framework for social media content-based recommendation system
by Adinarayana Salina; E. Ilavarasan; Yogeswara Rao Kalla
International Journal of Vehicle Information and Communication Systems (IJVICS), Vol. 7, No. 2, 2022

Abstract: Analysing huge volume of data from the social media tweets on product reviews provides a better understanding of any product. Exploring customer opinions from tweets is helpful to find the strengths and weaknesses of different products and features. There are several studies on product recommendations from Twitter product reviews. In this paper, Internet of Things-based two level product recommendation framework (TLPRF) is proposed to efficiently handle large amount of Twitter users' product reviews data. TLPRF consists of a Raspberry Pi microcomputer as an IoT mining machine and it is programmed to generate a feature level opinion summary. Feature level opinion is found to be useful in accomplishing the product ranking. Based on the customer interest in the product purchase request, a normalised ranking of each matching product is calculated from the feature-wise opinion summary and the product with maximum ranked score is recommended to Twitter user. The proposed TLPRF is found to be superior to similar other approaches in terms of accuracy, precision, recall and f-measure.

Online publication date: Tue, 03-May-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Vehicle Information and Communication Systems (IJVICS):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com