The impact of recommendation algorithms on user interaction in messengers
Abstract
The theses are dedicated to the study of the application of deep neural networks and the integration of multimodal data for building recommendation systems in messengers. The paper analyzes the impact of personalized recommendations on user interaction, particularly the increase in engagement and the improvement of user experience through the integration of textual, visual, and audio data. Special attention is given to modern methods such as vector representations and attention mechanisms, which ensure more accurate and relevant recommendations. The challenges of processing large volumes of multimedia data in real-time and the possibilities for optimizing these processes to enhance system performance are also discussed. Additionally, the prospects for further development of personalization in messengers is explored, taking into account changing user needs.
References
Jurafsky, D., & Martin, J. H. (2020). "Speech and Language Processing" (3rd Edition). Pearson.
Aggarwal, C. C. (2018). "Neural Networks and Deep Learning: A Textbook". Springer.
Zhang, T., Qin, Z., & Wu, D. (2020). "Sentiment Analysis for Software Engineering: A Systematic Mapping Study". IEEE Access.
Liu, B. (2012). "Sentiment Analysis and Opinion Mining". Morgan & Claypool Publishers.
Goldberg, Y. (2016). "A Primer on Neural Network Models for Natural Language Processing". Journal of Artificial Intelligence Research, 57, 345-420.
Yang, Y., Hu, H., Zhao, Y., Zhang, M., Ma, S., & Yin, J. (2017). "Personalized Recommendation System Based on Deep Learning: A Survey". IEEE Access.
Manning, C. D., Raghavan, P., & Schütze, H. (2008). "Introduction to Information Retrieval". Cambridge University Press.

