Алгоритм видобування та опрацювання споріднених даних в соціальних мережах

АЛГОРИТМ ВИДОБУВАННЯ ТА ОПРАЦЮВАННЯ СПОРІДНЕНИХ ДАНИХ В СОЦІАЛЬНИХ МЕРЕЖАХ

ALGORITHM OF DATA MINING AND PROCESSING  OF RELATED DATA IN SOCIAL NETWORKS

Сторінки 115–118. Номер: №4, 2022 (311)  
Автори:
КРИВЕНЧУК Ю. П.
Національний університет “Львівська політехніка”
https://orcid.org/0000-0002-2504-5833
e-mail: Yurii.P.Kryvenchuk@lpnu.ua
ХАНАС М.-Ю. Р.
Національний університет “Львівська політехніка”
e-mail: hanasura79@gmail.com
Yurii KRYVENCHUK, Mykhailo-Yurii KHANAS
Lviv Polytechnic National University
DOI: https://www.doi.org/10.31891/2307-5732-2022-311-4-115-118

Анотація мовою оригіналу

Основою даної роботи є один з алгоритмів, що використовуються в рекомендаційних системах – рекомендаційна система основана на фільтрації вмісту. Вона аналізує пости користувачів у Twitter та вираховує їх інтереси. Особливістю даної системи є те, що даний алгоритм використовує паралельні обчислення та частотний аналіз тексту. Це дає змогу об’єднати людей з однаковими інтересами.
Ключові слова: рекомендаційна система, дата майнінг, big data, nltk, tweepy.

Розширена анотація англійською  мовою

We live in a time of rapid growth of information technology, which is firmly entrenched in our daily lives. It is simply impossible to imagine a modern person without social networks, because they perform a communicative and informational function, namely: communication, information retrieval, news exchange, etc. Five hundred million tweets are posted daily, making Twitter a major social media platform from which topical information on events can be extracted. So, there is a lot of information available to the user, which is difficult to identify something specific and necessary in the usual way viewing. Accordingly, there is a need for technologies that can quickly process large amounts of data and highlight only the information that is useful to a particular user. This technology called recommender systems. It automatically suggest items to users that might be interesting for them. Due to the desire to unite people with common interests, it is relevant to develop a recommendation system based on social networks that help in personification of the user and compilation of his psychotype using his profile.
The paper has description and results of the creation of recommendation system. The basis of this work is one of the algorithms used in recommendation systems – the recommendation system is based on content filtering. It analyzes users’ Twitter posts and calculates their interests. If we consider all the words, our model will not have good results and do not pay attention to what is important to use. Therefore, the most important step is always filtering data, so the number one task is to speed up the time of filtering text and retrieving data from the social network for further processing. The feature of this system is that this algorithm uses parallel calculations and frequency analysis of the text.
Keywords: recommendation system, date mining, big data, nltk, tweepy.

Література

1. He, Z. He, X. Du, and T.-S. Chua, “Adversarial personalized ranking for recommendation,” in The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. ACM, 2018
2. Tang, X. Hu, and H. Liu, “Social recommendation: a review,” Social Network Analysis and Mining, vol. 3, no. 4, 2013.
3. C. Valverde-Rebaza, M. Roche, P. Poncelet, and A. D. A. Lopes, The role of location and social strength for friendship prediction in location-based social networks, Information Processing and Management, vol. 54, no. 4, 2018, doi: 10.1016/j.ipm.2018.02.004.
4. Zhao, Q. Yao, J. T. Kwok, and D. L. Lee, Collaborative filtering with social local models, 2017, vol. 2017-November, pp. 645–654. doi: 10.1109/ICDM.2017.74.
5. Liu, P. Zhao, X. Liu, M. Wu, and X.-L. Li. Learning Optimal Social Dependency for Recommendation. arXiv preprint arXiv:1603.04522, 2016.
6. Steven Bird, Ewan Klein, and Edward Loper, Natural Language Processing with Python, Analyzing Text with the Natural Language Toolkit, O’Reilly Media, 2009
7. Yu, M. Gao, J. Li, H. Yin, and H. Liu, “Adaptive implicit friends identification over heterogeneous network for social recommendation,” in Proceedings of the 27th ACM International Conference on Information and Knowledge Management. ACM, 2018
8. Davoudi and M. Chatterjee. Modeling trust for rating prediction in recommender systems. In SIAM Workshop on Machine Learning Methods for Recommender Systems, SIAM, 2016.

References

1. He, Z. He, X. Du, and T.-S. Chua, “Adversarial personalized ranking for recommendation,” in The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. ACM, 2018
2. Tang, X. Hu, and H. Liu, “Social recommendation: a review,” Social Network Analysis and Mining, vol. 3, no. 4, 2013.
3. C. Valverde-Rebaza, M. Roche, P. Poncelet, and A. D. A. Lopes, The role of location and social strength for friendship prediction in location-based social networks, Information Processing and Management, vol. 54, no. 4, 2018, doi: 10.1016/j.ipm.2018.02.004.
4. Zhao, Q. Yao, J. T. Kwok, and D. L. Lee, Collaborative filtering with social local models, 2017, vol. 2017-November, pp. 645–654. doi: 10.1109/ICDM.2017.74.
5. Liu, P. Zhao, X. Liu, M. Wu, and X.-L. Li. Learning Optimal Social Dependency for Recommendation. arXiv preprint arXiv:1603.04522, 2016.
6. Steven Bird, Ewan Klein, and Edward Loper, Natural Language Processing with Python, Analyzing Text with the Natural Language Toolkit, O’Reilly Media, 2009
7. Yu, M. Gao, J. Li, H. Yin, and H. Liu, “Adaptive implicit friends identification over heterogeneous network for social recommendation,” in Proceedings of the 27th ACM International Conference on Information and Knowledge Management. ACM, 2018
8. Davoudi and M. Chatterjee. Modeling trust for rating prediction in recommender systems. In SIAM Workshop on Machine Learning Methods for Recommender Systems, SIAM, 2016.