Text mining for news issue analysis
Hierarchical and incremental clustering of news articles, Korean word similarity, and applied data mining.
During my M.S. at UST-KISTI, I built a clustering module for semi-real-time issue analysis of Korean news articles, combining hierarchical and incremental clustering with word embeddings (Kim et al., 2019; Kim et al., 2020). Related work includes a word semantic similarity model built from the Korean Open Dictionary (Kim et al., 2018), a web crawler and network analysis pipeline for flood prediction (Seo et al., 2019), and applied prediction models for sports rankings (Jin et al., 2019) and traffic accident points (Kim et al., 2019).
References
2020
- JKCA
Hierarchical and Incremental Clustering for Semi-Real-time Issue Analysis on News ArticlesThe Journal of the Korea Contents Association, 2020in Korean
2019
- KSC
Hierarchical Clustering of News Articles for Semi-Real-time Issue AnalysisIn Korea Software Congress (KSC), Korean Institute of Information Scientists and Engineers, 2019in Korean - KCA
Development of Web Crawler and Network Analysis Technology for Occurrence and Prediction of FloodingIn Korea Contents Association Spring Conference (KCA), 2019in Korean - ICCC
Prediction of Korean Basketball League Playoff Power-Ranking Based on Recurrent Neural Networks Using KBL EfficiencyIn International Conference on Convergence Content (ICCC), Korea Contents Association, 2019 - HCI KoreaFeature Selection and Visualization Based on Expectation Maximization and Principal Component Analysis for Traffic Accidents Point PredictionJournal of the HCI Society of Korea, 2019in Korean
2018
- KCAA Word Semantic Similarity Measure Model Using Korean Open DictionaryIn Korea Contents Association Spring Conference (KCA), 2018in Korean