Deep Learning for Sentiment Analysis: a case study about Portuguese Restaurant Reviews

• Autor(a) principal: Parada, Daniel Moisés De Olival
• Data de Publicação: 2024
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10400.13/5605
• topic: Processamento de linguagem natural; Análise de sentimentos; Língua portuguesa; Aprendizagem profunda; Algoritmo genético; Dispositivo de borda; Natural language processing; Sentiment analysis; Portuguese language; Deep learning; Genetic algorithm; Edge computing; Electrical Engineering – Telecommunications; .; Faculdade de Ciências Exatas e da Engenharia; Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática

This work investigates the usage of deep learning algorithms to perform sentiment analysis over restaurant reviews from the Zomato application, making use of natural language processing techniques to handle text data and taking advantage of the rating given by consumers to perform supervised training. This work presents two models developed from scratch to address the case study problem using recurrent neural networks and self-attention: Recurrent Encoder Classifier and Attentive Recurrent Encoder Classifier. These models were subject to two heuristic-based optimization procedures: a discrete genetic algorithm to select an optimal set of hyperparameters and optimal architecture and a grid search algorithm to optimize the text preprocessing steps. The usage of deep learning models with Portuguese data is limited; hence, the gain in performance was evaluated against classical machine learning models trained on Zomato’s dataset, verifying an improvement of 3% in F1-score. The genetic algorithm yielded a relative obtainable improvement score of 4.4% and 8.3% on the recurrent and attentive recurrent encoders architectures, respectively, against their baseline configuration, with the possibility of further optimization by increasing the number of generations. The grid search algorithm slightly improved the performance of each architecture. Both had comparable results, where the Attentive Recurrent Encoder Classifier presented the best performance with 76% of F1-score, 92.5% of ROC-AUC, and 82.7% of accuracy. Tests on a Raspberry Pi application to use the model for inference demonstrated the feasibility of the proposed approach for sentiment analysis in real-world, resource-constrained environments. The results of the study demonstrate that deep learning algorithms can effectively analyze sentiment and show superior results to the traditional ML algorithms and supports the need of exploring smaller, single-task Deep Learning models in the transition of businesses to solutions based on artificial intelligence.