Ensemble Deep Learning Framework for Situational Aspects-Based Annotation and Classification of International Student's Tweets during COVID-19

As the COVID-19 pandemic swept the globe, social media plat-forms became an essential source of information and communication for many. International students, particularly, turned to Twitter to express their struggles and hardships during this difficult time. To better understand the sentiments and experiences of these international students, we developed the Situational Aspect-Based Annotation and Classification (SABAC) text mining framework. This framework uses a three-layer approach, combining baseline Deep Learning (DL) models with Machine Learning (ML) models as meta-classifiers to accurately predict the sentiments and aspects expressed in tweets from our collected Student-COVID-19 dataset. Using the pro-posed aspect2class annotation algorithm, we labeled bulk unlabeled tweets according to their contained aspect terms. However, we also recognized the challenges of reducing data's high dimensionality and sparsity to improve performance and annotation on unlabeled datasets. To address this issue, we proposed the Volatile Stopwords Filtering (VSF) technique to reduce sparsity and enhance classifier performance. The resulting Student-COVID Twitter dataset achieved a sophisticated accuracy of 93.21% when using the random forest as a meta-classifier. Through testing on three benchmark datasets, we found that the SABAC ensemble framework performed exceptionally well. Our findings showed that international students during the pandemic faced various issues, including stress, uncertainty, health concerns, financial stress, and difficulties with online classes and returning to school. By analyzing and summarizing these annotated tweets, decision-makers can better understand and address the real-time problems international students face during the ongoing pandemic.

Aspect oriented sentiment classification of COVID-19 twitter data;An enhanced LDA based text analytic approach

Social media has become one of the most important sources of information dissemination during crisis and pandemics. The unknown nature of these disasters makes it hard to analyze the comprehensive situational awareness through different aspects and sentiments to support authorities. Current aspect detection and sentiment analysis system largely relies on labelled data and also categorize the aspects manually. So, in this research, we proposed a hybrid text analytical framework to do aspect level public sentiments analysis. Our approach consists of three layers, first we extracted and clustered the aspects from the data by utilizing the widely used Latent dirichlet allocation (LDA) topic modelling, then we extracted the sentiments and label the dataset by using the linguistic inquiry and word count (LIWC) lexicon, then in third layer of our framework we mapped the aspects into sentiments and sentiments are then classified with well-known machine learning classifiers. Experiments with real dataset gives us promising results as compared to existing aspect oriented sentiment analysis approaches and our method with different variant of classifiers outperforms existing methods with highest F1 scores of 91 %. © 2021 IEEE.