Research Trending Topic Prediction as Cognitive Enhancement

• Published in: Proceedings (International Conference on Cyberworlds. Online) pp. 217 - 220
• Main Authors: Charnine, Michael, Klokov, Alexey, Kochiev, Leon, Tishchenko, Alexey
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2021
• Subjects: Big Data; CatBoost; cognitive enhancement; decision tree; dynamics of topic trends; long-term prediction; research trending topics; scientific papers
• ISSN: 2642-3596
• DOI: 10.1109/CW52790.2021.00044

The Internet has been identified in human enhancement scholarship as a powerful cognitive enhancement technology. Using the Internet as an external memory system has overall benefits if we have the skills to efficiently navigate, evaluate, and compare online information. Long-term prediction of research trending topics is a form of cognitive enhancement because it helps to efficiently navigate, evaluate scientific articles, identify promising directions, and focus efforts in these directions. This paper presents the results of a method designed to realize long-term prediction of research trending topics. Meaningful topics were identified among the words included in the titles of scientific articles. The title is the most important element of a scientific article and the main indication of the article's subject and topic. We treated the title words, which occur several times in cited articles of the analyzed collection, as the research trending topics. The longevity of the citation trend growth was the target for the machine learning algorithms. The CatBoost machine learning method, which is one of the best implementations of decision trees, was used. We conducted experiments on a scientific dataset including 5 million publications of top conferences in artificial intelligence and data mining areas to demonstrate the effectiveness of the proposed model. The accuracy rate of three-year forecasts for a number of experiments from 1997 to 2014 was about 60%.