The exponential rise in social media via microblogging sites like Twitter has sparked curiosity in sentiment analysis that exploits user feedback towards a targeted product or service. Considering its significance in business intelligence and decision-making, numerous efforts have been made in this area. However, lack of dictionaries, unannotated data, large-scale unstructured data, and low accuracies have plagued these approaches. Also, sentiment classification through classifier ensemble has been underexplored in literature. In this article, we propose a Semantic Relational Machine Learning (SRML) model that automatically classifies the sentiment of tweets by using classifier ensemble and optimal features. The model employs the Cascaded Feature Selection (CFS) strategy, a novel statistical assessment approach based on Wilcoxon rank sum test, univariate logistic regression assisted significant predictor test and cross-correlation test. It further uses the efficacy of word2vec-based continuous bag-of-words and n-gram feature extraction in conjunction with SentiWordNet for finding optimal features for classification. We experiment on six public Twitter sentiment datasets, the STS-Gold dataset, the Obama-McCain Debate (OMD) dataset, the healthcare reform (HCR) dataset and the SemEval2017 Task 4A, 4B and 4C on a heterogeneous classifier ensemble comprising fourteen individual classifiers from different paradigms. Results from the experimental study indicate that CFS supports in attaining a higher classification accuracy with up to 50% lesser features compared to count vectorizer approach. In Intra-model performance assessment, the Artificial Neural Network-Gradient Descent (ANN-GD) classifier performs comparatively better than other individual classifiers, but the Best Trained Ensemble (BTE) strategy outperforms on all metrics. In inter-model performance assessment with existing state-of-the-art systems, the proposed model achieved higher accuracy and outperforms more accomplished models employing quantum-inspired sentiment representation (QSR), transformer-based methods like BERT, BERTweet, RoBERTa and ensemble techniques. The research thus provides critical insights into implementing similar strategy into building more generic and robust expert system for sentiment analysis that can be leveraged across industries.

No abstract

Airlines operate in a competitive marketplace and must upgrade their services to meet customer safety and comfort. Post-pandemic, the government and airlines resumed flights with many restrictions, the impact which is unexplored. An increasing number of customers use social media to leave reviews and in this age of Machine Learning (ML), if a model is available to automatically polarize flyer sentiments, it can help airlines upscale. In this work, a custom dataset is scraped from Twitter by including online reviews of five Indian airlines. Multiclass sentiment analysis using three classifiers, support vector machine, K-nearest neighbor and random forest with word2vec and TF-IDF word embeddings is implemented. AirBERT, a fine-tuned deep learning attention model based on bidirectional encoder representation from transformers is proposed. From results, it is observed that on ML, Random Forest with TF-IDF performs the best but the graphical processing unit and domain corpora trained AirBERT outperforms all the other models with an accuracy of 91%. Indigo airlines and Jet Airways received the maximum percentage of positive and negative reviews respectively. In performance comparison with three existing models on the USA airlines tweets dataset, the proposed model outperforms others trained on general domain corpora and matches state-of-the-art TweetBERTv2 model accuracy. The model can be deployed by airlines and other service industries to implement a customer relationship management (CRM) system.

India has the highest circulation of newspapers in the world, but unfortunately also has high media bias rates and one of the lowest press freedom rankings for democracies. A biased media prevents citizens from receiving information that might be essential to public wellbeing by filtering information through a lens that supports government interests first. Media bias plays an influencing role even at the voting booth as propaganda can skew voter decisions and perceptions of what is true in this era of fake news. It's vital to keep an eye on bias in the news and to provide a platform where people can get unbiased and reliable news. Researchers in sentiment analysis and bias detection have been using various techniques to achieve higher accuracy to detect media bias. This study aims to take a different technical approach to the problem of Indian political media bias detection by developing SentiNet - a graphical processing unit (GPU) accelerated modified convolution neural network (CNN) model consisting of linearly inverted depth-wise separable convolutions capable of classifying news as either ‘unbiased’ or ‘biased’ from twitter data. Because of its simple architecture and lesser number of tuning parameters, it is observed that SentiNet is a good fit in terms of accuracy and loss function and its training time reduces by 50% when using a GPU. From results, Republic TV and BBC emerged as the most biased towards ruling party and Opposition parties respectively. NDTV and News19 emerged unbiased towards ruling party with balanced reporting. India TV has emerged as unbiased towards Opposition parties. From twitter political discourse, it is found that parties discuss themselves or their opposing parties and seldom issues of national interest. The research and the proposed robust model can be extended to other social media and be analysed for a bigger social network.

No abstract