Aspect-Based Sentiment Analysis and Emotion Detection for Code-Mixed Review

Abstract

Review can affect customer decision making because by reading it, people manage to know whether the review is positive, or negative. However, positive, negative, and neutral, without considering the emotion will be not enough because emotion can strengthen the sentiment result. This study explains about the comparison of machine learning and deep learning in sentiment as well as emotion classification with multilabel classification. In machine learning comparison, the problem transformation that we used are Binary Relevance (BR), Classifier Chain (CC), and Label Powerset (LP), with Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), and Extra Tree Classifier (ET) as algorithms of machine learning. The features we compared are n-gram language model (unigram, bigram, unigram-bigram). For deep learning, algorithms that we applied are Gated Recurrent Unit (GRU) and Bidirectional Long Short-Term Memory (BiLSTM), using selfdeveloped word embedding. The comparison results show RF dominates with 88.4% and 89.54% F1 scores with CC method for food aspect, and LP for price, respectively. For service and ambience aspects, ET leads with 92.65% and 87.1% with LP and CC methods, respectively. On the other hand, in deep learning comparison, GRU and BiLSTM obtained similar F1-score for food aspect, 88.16%. On price aspect, GRU leads with 83.01%. However, for service and ambience, BiLSTM achieved higher F1score, 89.03% and 84.78%.

From Multilingual Complexity to Emotional Clarity: Leveraging Commonsense to Unveil Emotions in Code-Mixed Dialogues

“…Emotion and code-mixing. Existing research on emotion analysis for code-mixed language primarily focuses on standalone social media texts (Sasidhar et al, 2020;Ilyas et al, 2023;Wadhawan and Aggarwal, 2021) and reviews (Suciati and Budi, 2020;Zhu et al, 2022). While aspects such as sarcasm (Kumar et al, 2022a,b), humour (Bedi et al, 2023), and offense (Madhu et al, 2023) have been explored within code-mixed conversations, emotion analysis remains largely an uncharted territory with no relevant literature available, to the best of our knowledge.…”

Annotated Lexicon for Sentiment Analysis in the Bosnian Language

“…There has been quite extensive research in the area of sentiment analysis, and many types of models and algorithms have been proposed depending on the final goal of the analysis of the interpretation of user feedback and queries, such as fine-grained sentiment analysis (based on polarity precision) (Chen et al, 2020), emotion detection, aspect-based sentiment analysis (Suciati and Budi, 2020), and multilingual sentiment analysis (Kia et al, 2016). All those algorithms and models can be divided into one of three basic classes: rule-based systems (relying on long-used linguistic methods, rules, and annotated linguistic materials such as annotated lexicons), automatic (corpus-based) systems, and hybrid systems that combine properties from both previous types.…”

Sentiment Analysis of Customer Reviews of Food Delivery Services Using Deep Learning and Explainable Artificial Intelligence: Systematic Review

“…According to some researchers [33,42], DL algorithms (bidirectional long short-term memory (Bi-LSTM) and simple embedding and average pooling) outperform traditional ML algorithms in sentiment classification and review rating prediction. They proposed the use of DL technique during the COVID-19 pandemic to help customers in making safe dining decisions.…”