• Yogaraj j
• Mohammed Sahith S
• Naveen N
• Venkatramanan M
• Jegathesh P

An aspect-based sentiment analysis method applied to Coursera course feedback data is presented in this paper. To gain a deeper knowledge of learners thoughts and experiences, the goal is to extract sentiment information with finer details related to various course features. The process includes gathering data, identifying aspects, classifying sentiment, training and assessing models, and integrating the findings. We go over how the feedback data is gathered, pre processed, course aspects are identified, and sentiment connected with each aspect is categorized. Using machine learning techniques, the sentiment analysis model is trained and assessed. The outcomes are combined to give thorough sentiment evaluations for Coursera courses. Reviews, ratings, and comments submitted by students across a variety of subjects and topics on the Coursera platform make up the dataset. We pre process the feedback data with algorithms for natural language processing to find important topics that students brought up. After that, we classify each aspect's sentiment using machine learning techniques, distinguishing between favourable, adverse, and neutral sentiments. The resulting accuracy rate is 88% for the reported results. Our approach facilitates the extraction of nuanced sentiment insights, enabling course providers to determine advantages and disadvantages and make data-driven improvements to course offerings. The project's results include thorough sentiment assessments of Coursera courses that point out their advantages and disadvantages in a number of areas. In order to better address the varied needs of learners, these insights enable course providers, instructors, and educational institutions to make data-driven decisions, improve platform features, and improve course design and instructional methodologies. This survey paper examined the ideas and efficacy of several textual emotion detection model, technique, and methodology categories.

Aspect-Based, Sentiment Analysis, Coursera Feedback, Sentiment Analysis, Machine learning

"Analyzing Sentiments in Coursera Course Feedback: An Aspect-Based ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.c413-c420, April-2024, Available :http://www.jetir.org/papers/JETIR2404248.pdf

"Analyzing Sentiments in Coursera Course Feedback: An Aspect-Based ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppc413-c420, April-2024, Available at : http://www.jetir.org/papers/JETIR2404248.pdf