D
Deokseong Seo
Researcher at Korea Electric Power Corporation
Publications - 3
Citations - 285
Deokseong Seo is an academic researcher from Korea Electric Power Corporation. The author has contributed to research in topics: Transfer of learning & Customer satisfaction. The author has an hindex of 2, co-authored 3 publications receiving 144 citations. Previous affiliations of Deokseong Seo include Korea University.
Papers
More filters
Journal ArticleDOI
Multi-co-training for document classification using various document representations: TF–IDF, LDA, and Doc2Vec
TL;DR: This paper transforms a document using three document representation methods: term frequency–inverse document frequency (TF–IDF) based on the bag-of-words scheme, topic distribution based on latent Dirichlet allocation (LDA), and neural-network-based document embedding known as document to vector (Doc2Vec).
Journal ArticleDOI
Unusual customer response identification and visualization based on text mining and anomaly detection
TL;DR: This study proposes a framework for identifying unusual but significant customer responses and frequently used words therein based on distributed document representation, local outlier factor, and TF–IDF methods and can accelerate the efficiency and effectiveness of many VOC data analytics.
Journal ArticleDOI
Facebook Spam Post Filtering based on Instagram-based Transfer Learning and Meta Information of Posts
TL;DR: This study develops a text spam filtering system for Facebook based on two variable categories: keywords learned from Instagram and meta-information of Facebook posts, and expects that the proposed filtering scheme can be applied other web services suffering from massive spam posts.