MBi-GRUMCONV: A novel Multi Bi-GRU and Multi CNN-Based deep learning model for social media sentiment analysis

Abstract

Today, internet and social media is used by many people, both for communication and for expressing opinions about various topics in many domains of life. Various artificial intelligence technologies-based approaches on analysis of these opinions have emerged natural language processing in the name of different tasks. One of these tasks is Sentiment analysis, which is a popular method aiming the task of analyzing people’s opinions which provides a powerful tool in making decisions for people, companies, governments, and researchers. It is desired to investigate the effect of using multi-layered and different neural networks together on the performance of the model to be developed in the sentiment analysis task. In this study, a new, deep learning-based model was proposed for sentiment analysis on IMDB movie reviews dataset. This model performs sentiment classification on vectorized reviews using two methods of Word2Vec, namely, the Skip Gram and Continuous Bag of Words, in three different vector sizes (100, 200, 300), with the help of 6 Bidirectional Gated Recurrent Units and 2 Convolution layers (MBi-GRUMCONV). In the experiments conducted with the proposed model, the dataset was split into 80%-20% and 70%-30% training-test sets, and 10% of the training splits were used for validation purposes. Accuracy and F1 score criteria were used to evaluate the classification performance. The 95.34% accuracy of the proposed model has outperformed the studies in the literature. As a result of the experiments, it was found that Skip Gram has a better contribution to classification success.

Regular paper Comparative Analysis of Deep Learning Models for Sentiment Analysis on IMDB Reviews

“…Additionally, it is often referred to as idea mining, and the terms sentiment, opinion, and impact are frequently used interchangeably. Emotion classification can be categorized into a pair of main strategies: machine learning-based and dictionary-based methods [4].…”

Textual emotion analysis using improved metaheuristics with deep learning model for intelligent systems

“…The features can be extracted by one of the utilized audio features called as MFCCs (Mel Frequency Cepstral Coefficients). In Reference 21, a novel DL‐based approach can be presented for SA on the IMDB movie reviews database. This method carries out sentiment classification on vectorised reviews utilizing two methods of Word2Vec such as Skip Gram and Continuous Bag of Words (BoW) in three various vector sizes (100, 200, 300), with the use of six BiGRU and two convolutional layers (MBi‐GRUMCONV).…”

Machine learning for sentiment analysis in social networks data: Advances and perspectives

“…The compared supervised learning algorithms are SVM (Karthika et al, 2019), (Moshkin et al, 2019), (Başarslan & Kayaalp, 2020), (Chintalapudi et al, 2021), (Mostafa et al, 2021), (AlBadani et al, 2022, (Rahman et al, 2022); Clustering-based Adaptive SVM (CA-SVM) (Cyril et al, 2021); LR (Moshkin et al, 2019), (Chintalapudi et al, 2021); (Mostafa et al, 2021); BRDT (Alatabi & Abbas, 2020); DT (Alatabi & Abbas, 2020); NB (Başarslan & Kayaalp, 2020), (Goel et al, 2018), (Khan & Malviya, 2020), (Moshkin et al, 2019), (Mostafa et al, 2021), (Rahman et al, 2022); KNN (Mostafa et al, 2021) and RF (Karthika et al, 2019); combined in some cases with the natural language processing techniques like BoW (Carvalho & Harris, 2020), (AlBadani et al, 2022, (Rahman et al, 2022); TF-IDF (Rustam et al, 2021), (Salmony & Faridi, 2021), (Rahman et al, 2022); Word2Vec (Başarslan & Kayaalp, 2020), (Rahman et al, 2022), (Başarslan & Kayaalp, 2023); and PSO (Başarslan & Kayaalp, 2020).…”