Title: Transforming recommender system by integrating attention-based neural network for multimodal sentiment analysis using artificial intelligence

Authors: V. Vinitha; S.K. Manju Bargavi

Addresses: Jain (Deemed to be University), Bengaluru, Karnataka, India ' Jain (Deemed to be University), Bengaluru, Karnataka, India

Abstract: Sentiment analysis represents an emerging field of study in both natural language processing and computational intelligence. Recommender systems play a pivotal role in enhancing user experiences across various platforms by suggesting personalised content based on user preferences. However, conventional recommender systems often lack the capability to understand the nuanced sentiments associated with multimedia content, such as textual and visual clues which are increasingly prevalent in the digital landscape. This study proposes the architecture of a deep multi-view attention-based network model. Attention-based multimodal sentiment classification combines convolutional neural networks for image data with bidirectional encoder representations from transformers for textual data. The synergy between these two modalities enhances the model's capability of capturing abundant contextual information and visual signals. Extensive experiments on the publicly available interactive emotional dyadic motion capture data set show that the suggested method performs with an accuracy of 99.87% in capturing complicated sentiment patterns across multiple domains.

Keywords: sentiment analysis; recommender system; artificial intelligence; natural language processing; BERT; multimodal analysis; convolutional neural networks.

DOI: 10.1504/IJCAT.2024.141373

International Journal of Computer Applications in Technology, 2024 Vol.74 No.1/2, pp.136 - 145

Received: 31 Oct 2023
Accepted: 05 Jun 2024
Published online: 09 Sep 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article