Customer Sentiment Based Online Grocery Recommendation Engine
Customer Sentiment Based Online Grocery Recommendation Engine
Customer Sentiment Based Online Grocery Recommendation Engine
ISSN No:-2456-2165
Online shopping is a good way as it helps the Thousands upon thousands of online shoppers
customers or users to easily shop for anything just through regularly share their opinions on social media and review
the internet. One of the main reasons for slow sales is the websites.
negative product range. Sentiment analysis plays an
important role as it shows sellers how effective customer Scrutinizing this publicly available client data lets in
reviews can be. Every opinion counts, whether it is good or patterns to be detected and a photograph to be compiled of
bad. Sentiment analysis evaluates the reviews and suggests your patron’s mind-set. This procedure is called sentiment
the items for the client to purchase. The Internet, known as analysis. In the age of social media websites, it has been
the danger of angles and the possibility to access these easier for internet users to share and rate their reviews
reviews on different platforms is a great advantage for any regarding unique aspects of their lifestyle, including services
company that wants to improve its services or products. and product.
Step 3: Enhancement
Through tokenization, every token is converted into a tuple (phrase, tag) by splitting the text.
Prevent words in English are the words that carry little or no beneficial facts. We want to eliminate words as a role oftextual
content for error checking, nltk owns a listing for forestall words for each language.
Tb_count = fin_data. Analysis.Value_counts () tb_cou thetotal of positive, negative, and neutra; potency supply .
The data degrees from -1 to one and is the metric used to attach overall emotions. +ve data >= 0.5 neutral i-zero. Five
< data< 0.5
V. RESULTS
REFERENCES
[1.] Lei Zhang, Shuai Wang, Bing lui “data mining and
knowledge discovery” vol.8 , issue 4, August 2018
[2.] V.K. Singh, r. Piryani, a. Uddin p. Waila, Marisha
“sentiment evaluation of remember reviews,
evaluating system learning, unattended and senti
word net approaches” continuing in IEEE 2013 fifth
international convention on information and realistic
technology (kit)
[3.] Shenglei Chen, Geoffrey I. Webb, Linyuan Liu, Xin
Ma “a novel selective naïve Bayes algorithm,
knowledge-based systems”,vol.192, 15 March2020
[4.] Mehdi Elahi ,Sorush Saghari, Danial Khosh Kholgh,
“Information Sciences”, vol. 625,May 2023
[5.] Sayantani Ghosh, Mr. Sudipta Roy, and prof. Samir
k., “an academic overview on textual content mining
algorithms”, international journal of advanced
analysis in computer and conversation engineering,
pages: 223-233, vol. 1, problem 4, June2012
[6.] Christopherd. Manning, Prabhakar Raghavan,
hinrichsch¨utze, “introduction to information
retrieval”, ISBN-13 978-0-511-41405-3, 2013.
[7.] J. Jumanto, M. A. Muslim, Y. Dasril, and T.
Mustaqim, “Accuracy of Malaysia Public Response
to Economic Factors During the Covid-19 Pandemic
Using Vader and Random Forest”, J. Inf. Syst.
Explor. Res., vol. 1, no. 1, pp. 49 - 70, Dec. 2022.
[8.] Li Chen, Dongning Yan, Feng Wang “User
perception of sentiment-integrated critiquing in
recommender systems,International Journal of
Human-Computer Studies”, vol.121,January 2019.
[9.] M. Wongkar and A. Angdresey, "Sentiment Analysis
Using Naive Bayes Algorithm Of The Data Crawler:
Twitter," 2019 Fourth International Conference on