Analysis of Learners' Sentiments on MOOC Forums using Natural Language Processing Techniques

MOOCs have gained a lot of popularity for past few years. Especially after the outbreak of Coronavirus, everyone is trying to gain some knowledge and skill while being at the comfort of home and making themselves safe. Due to sudden increase in the number of participants on MOOCs there is a need for an automated system to be able to assess the reviews and feedbacks given by the learners and find the sentiments behind their statements. This analysis will help trainers identify their shortcoming and make their courses even better. For sentiments analysis, several approaches may be used. This research aims to provide a system which will perform sentiments analysis on the novel dataset and show the comparison of lexicon-based vs transformer-based sentiment analysis models. For lexicon based, VADER was chosen and for transformer-based, state-of-The-Art BERT was chosen. BERT was found to be exceptionally good with an accuracy of 84% and F1-score of 0.64. © 2022 IEEE.

CoSaD-Code-Mixed Sentiments Analysis for Dravidian Languages

Analyzing sentiments or opinions in code-mixed languages is gaining importance due to increase in the use of social media and online platforms especially during the Covid-19 pandemic. In a multilingual society like India, code-mixing and script mixing is quite common as people especially the younger generation are quite familiar in using more than one language. In view of this, the current paper describes the models submitted by our team MUCIC for the shared task in’Sentiments Analysis (SA) for Dravidian Languages in Code-Mixed Text’. The objective of this shared task is to develop and evaluate models for code-mixed datasets in three Dravidian languages, namely: Kannada, Malayalam, and Tamil mixed with English language resulting in Kannada-English (Ka-En), Malayalam-English (Ma-En), and Tamil-English (Ta-En) language pairs. N-grams of char, char sequences, and syllables features are transformed into feature vectors and are used to train three Machine Learning (ML) classifiers with majority voting. The predictions on the Test set obtained average weighted F1-scores of 0.628, 0.726, and 0.619 securing 2nd, 4th, and 5th ranks for Ka-En, Ma-En, and Ta-En language pairs respectively. © 2021 Copyright for this paper by its authors.

UAE e-learning sentiment analysis framework

This research project predicts and infers real-time insights on public mental health relevant to education during and after the COVID-19 pandemic by modeling, deploying, and testing an end-to-end spatiotemporal sentiment analysis framework. Moreover, the project aims to analyze the sentiments and emotions of the public;from Twitter, toward the current context of the e-learning process factored by aspects and emotions. The framework consists of four predictive models based on statistical analysis and machine learning to analyze the UAE education-related Twitter dataset. The first analytics is spatiotemporal analytics, which describes an event at a specific time and specific location. Spatiotemporal analytics is used as the base for the remaining three analytics: Aspect-based Sentiment Analysis, sentiment analysis, and emotion analysis. Aspectbased Sentiment Analysis considers the words/terms related to relevant aspects and then identify the sentiment associated with them. Sentiment Analysis is used to extract the sentiment in a specific text. Emotion Analysis identifies the type of emotion felt by users in their tweets. All the analytics will be visualized into a responsive website that provides a prompt understanding of the public opinions and their feedback towards the e-learning process. As a result, a group of recommendations is generated based on the analytics' resulting emotion to enhance the mental health. © 2021 Association for Computing Machinery.