Online research opinion mining and sentiment analysis of college and school going students may accurately represent the students learning circumstances, providing the theoretical foundation for further revisions of teaching programmes. Analysis of student learning experiences using data mining and sentiment analysis in online learning community may lay the theoretical groundwork for future changes to teaching programmes. The term "online study" is the study that takes place using the internet. One of the objectives of the project is the creation and assessment of a conceptual model that incorporates students` learning and teaching preferences as well as technological experience, as well as their feelings about how these things impact their learning and teaching. An online survey of college and school going students was performed. It was found that some clusters of students were formed after applying k-means clustering machine learning algorithm which shows us that some changes should be adopted in the current online study scenario. Prediction and visualization of the data is done by seaborn, matplotlib python libraries which helps us to understand the pattern of the data. It is expected that this assessment would create a better system for students to study. Discoveries corroborate hypotheses about the influence of sentiment on factors such as attitude, favorite hobbies, and technological experience.

online study, sentiment analysis, python, machine learning, clustering, k-means sert

[1]. Carnelley, K. B. & Rowe, A. C. Priming a sense of security: what goes through people’s minds? Journal of Social and Personal Relationships, vol.27, Issue 2,PP 253-261,2010
[2]. Kaklauskas, A., Zavadskas, E.K., Seniut, M.,” Recommender system to analyze student’s academic performance”, Expert Systems with Applications ,vol 40,Issue 15,PP 6150-6165,2013
[3]. Chu, K.M., & Li, F.,“Topic evolution based on LDA and topic association” J. Shanghai Jiao tong Univ. (Sci),vol. 44,Issue 11, PP 1501–1506,2010.
[4].Cerulo, L., & Distante, D,“Topic-driven semi-automatic reorganization of online discussion forums: A case study in an e-learning context”. Global Engineering Education Conference. IEEE, March 13–15, Berlin, Germany,2013.
[5]. Chen, Y.C. A novel algorithm for mining opinion leaders in social networks. World Wide Web-internet & Web Information Systems. 2018.
[6].Ethem, F.C., Aysu, E.C., & Fazli, C. ,“Multilingual sentiment analysis: An RNN-based framework for limited data” arXiv: 1806.04511,2018.
[7]. Colace, F., De Santo, M., & Greco, L.,“SAFE: A sentiment analysis framework for e-Learning” International Journal Of Emerging Technologies In Learning (IJET), vol 9 Issue 6, PP 37–41.,2014.
[8]. Gao, G., Luo J.M., & Wang, Y.,“Robust visual-textual sentiment analysis: When attention meets tree-structured recursive neural networks” 24th ACM international conference on multimedia, pp 1008-1017,2016.
[9]. Kohoulat, N., Hayat, A.A., Dehghani, M.R., Kojuri, J., & Amini, M.,“Medical students’ academic emotions: the role of perceived learning environment” Journal of Advances in Medical Education & Professionalism, vol 5,Issue2, 2017.
[10]. Hady, M.F.A., & Schwenker, F.,” Co-training by Committee: A New Semi-supervised Learning Framework” Workshops IEEE International Conference on Data Mining,2008.
[11].Vinodhini, G., “Sentiment mining using SVM-based hybrid classification model”. Advances in Intelligent Systems & Computing, volume 246, 2013.
[12]. Wang, J., Zuo, W., & Tao, P.,“Hyponymy graph model for word semantic similarity measurement”, Chinese Journal of Electronics, vol.24,Issue 1,2015.
[13].Zhang, Y.F., Li, H., Peng, L.H., & Hou, L.T.,“The usefulness classification algorithm and application of online reviews based on emotional semantic feature extraction” Data Analysis and Knowledge Discovery, volume1,Issue12,2017.
[14].Kanwar, A.; Daniel, J. Report to Commonwealth Education Ministers: From Response to Resilience; Commonwelath of Learning: Burnaby, BC, Canada, 2020.
[15]. Reema Tareja, “Data warehousing” ,2009