top of page

Classification of Customers' Sentiment

In collaboration with the marketing team, I developed a sentiment analyzer for Daraz to understand customer sentiment during the 12.12 campaign. This project enables Daraz to classify customer sentiment and make data-driven decisions to improve customer satisfaction.

Problem Statement: During the 12.12 campaign of Daraz, understanding customers' sentiment towards the campaign was important. Without a proper understanding of customer sentiment, the marketing team would not be able to properly analyze how customers interact with Daraz.


Proposed Solution: This project aims to conduct sentiment analysis to mine the sentiments of customers regarding their purchases from Daraz during the 12.12 campaign. Findings show that the model's accuracy is 95.33%, precision is 95% and kappa statistics value of 0.93 (>0.7 is a very good model). This model helps to classify the sentiment of customers who shop at Daraz and also provide predicted sentiment. By classifying the sentiment, companies like Daraz can dig into what is causing more negative sentiment among customers and try to enhance customer satisfaction.

Project Details Summary

Technical Skills

Sentiment Analysis using Naive Bayes Multinomial Model in Weka

Developed For

Daraz (Alibaba Group)

bottom of page