Sentiment analysis, the process of determining the emotional tone of a text, is essential for comprehending user opinions and preferences. Unfortunately, the majority of research on sentiment analysis has focused on reviews written in English, leaving a void in the study of reviews written in other languages. This research focuses on the understudied topic of sentiment analysis of Bangla-language product reviews. The objective of this study is to compare the performance of machine learning models for binary and multiclass sentiment classification in the Bangla language in order to gain a deeper understanding of user sentiments regarding e-commerce product reviews. Creating a dataset of approximately one thousand Bangla product reviews from the e-commerce website 'Daraz', we classified sentiments using a variety of machine learning algorithms and natural language processing (NLP) feature extraction techniques such as TF-IDF, Count Vectorizer with N-gram methods. The overall performance of machine learning models for multiclass sentiment classification was lower than binary class sentiment classification. In multiclass sentiment classification, Logistic Regression with bigram count vectorizer achieved the maximum accuracy of 82.64%, while Random Forest with unigram TF-IDF vectorizer achieved the highest accuracy of 94.44%. Our proposed system outperforms previous multiclass sentiment classification techniques by a fine margin.

After release of Web 2.0 in 2004 user spawned contents on the internet eminently in abundant review sites, online forums, online blogs, and many other sites. Entire user generated contents are considerable bunches of unorganized text written in different languages that encompass user emotions about one or more entities. Mainly predictive analysis exerts the existing data to forecast future outcomes. Currently, a massive amount of researches are being engrossed in the area of opinion mining, also called sentiment analysis, opinion extraction, review analysis, subjective analysis, emotion analysis, and mood extraction. It can be an utmost choice whilst perceiving the meaning and patterns in prevailing data. Most of the time, there are various algorithms available to work with polling. There are contradictory opinions among researchers regarding the effectiveness of algorithms. We have compared different opinion mining algorithms and presented the findings in this paper.

The main purpose of higher education is to produce skilled graduates so that they can think critically and solve real world problems. Presenting a group based solution in a face-to-face class is a common activity in the higher education classroom where other students/peers can actively participate in the follow-up question/answer sessions. Working out a solution together as a group engages students’ independent thinking ability and promotes active learning. This means, that they have the opportunity to reflect on their own thinking and take it to deeper levels of thinking. However, recent trends show that online support to the higher education class - a form of blended learning is growing day by day. This paper proposes a wiki-based (one of the ICT tools) reflection method to follow up regular existing face-to-face classroom presentation activities to promote deeper thinking levels of students in higher education. In this article, Lee’s Model of thinking levels is-used for analyzing the thinking levels of students during their wiki work. The findings of this research work (through experiments) show that the wiki-based reflection method could be an effective way to promote thinking levels of students and hence can be used as a blended learning model to promote reflective and in-depth thinking.