Home / Current Issue / Paper 1704684
Enhancing Personalized Recommendations: A Spacy-Based Hybrid Approach for Book Recommendation Systems
Subject area: Science,Engineering and Technology · Area of research: Computer Science
Abstract
Recommendation systems have become ubiquitous in our digital age, with various platforms utilizing algorithms to predict what items users might be interested in and offer personalized recommendations. To build more effective recommendation models, it is essential to analyse and understand natural language, such as product descriptions or user reviews. Tokenization, part-of-speech tagging, named entity recognition, dependency parsing, and other features offered by Spacy, an open-source NLP toolkit, are effective tools that may be used to extract meaning from natural language text. Using Spacy, it is possible to identify the key topics or themes of a product description or review and match them to the interests of individual users. Spacy's speed and scalability make it well-suited for real-time recommendation systems that need to process large volumes of data quickly. As such, Spacy has become increasingly popular among researchers and practitioners working in this area, due to its unique set of NLP features and capabilities.
References
[1] Su, Xiaoyuan, and Taghi M. Khoshgoftaar. "A survey of collaborative filtering techniques." Advances in artificial intelligence 2009 (2009).
[2] Lops, Pasquale, Marco De Gemmis, and Giovanni Semeraro. "Content-based recommender systems: State of the art and trends." Recommender systems handbook (2011): 73-105.
[3] Burke, R. (2002). "Hybrid Recommender Systems: Survey and Experiments." User Modeling and User-Adapted Interaction, 12(4), 331-370.
[4] Covington, Paul, Jay Adams, and Emre Sargin. "Deep neural networks for youtube recommendations." Proceedings of the 10th ACM conference on recommender systems. 2016
[5] Vasiliev, Yuli. Natural language processing with Python and spaCy: A practical introduction. No Starch Press, 2020.
[6] Wan, Mengting, et al. “Fine-Grained Spoiler Detection from Large-Scale Review Corpora.” ACL Anthology, 31 May 2019, aclanthology.org/P19-1248.
[7] Mengting Wan and Julian McAuley. 2018. Item recommendation on monotonic behavior chains. In Proceedings of the 12th ACM Conference on Recommender Systems (RecSys '18). Association for Computing Machinery, New York, NY, USA, 86–94. https://doi.org/10.1145/3240323.3240369
[8] Singhal, Amit. Modern Information Retrieval: A Brief Overview. singhal.info/ieee2001.pdf.
How to cite this paper
@article{1704684,
author = {Jayank Tyagi, Vandana Choudhary, Namita Goyal},
title = {Enhancing Personalized Recommendations: A Spacy-Based Hybrid Approach for Book Recommendation Systems},
journal = {Iconic Research And Engineering Journals},
year = {2023},
volume = {6},
number = {12},
pages = {550-557},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1704684.pdf},
abstract = {Recommendation systems have become ubiquitous in our digital age, with various platforms utilizing algorithms to predict what items users might be interested in and offer personalized recommendations. To build more effective recommendation models, it is essential to analyse and understand natural language, such as product descriptions or user reviews. Tokenization, part-of-speech tagging, named entity recognition, dependency parsing, and other features offered by Spacy, an open-source NLP toolkit, are effective tools that may be used to extract meaning from natural language text. Using Spacy, it is possible to identify the key topics or themes of a product description or review and match them to the interests of individual users. Spacy's speed and scalability make it well-suited for real-time recommendation systems that need to process large volumes of data quickly. As such, Spacy has become increasingly popular among researchers and practitioners working in this area, due to its unique set of NLP features and capabilities.},
month = {June},
}