The Power of Communities: A Text Classification Model with Automated Labeling Process Using Network Community Detection

Minjun Kim, Hiroki Sayama

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Text classification is one of the most critical areas in machine learning and artificial intelligence research. It has been actively adopted in many business applications such as conversational intelligence systems, news articles categorizations, sentiment analysis, emotion detection systems, and many other recommendation systems in our daily life. One of the problems in supervised text classification models is that the models’ performance depends heavily on the quality of data labeling that is typically done by humans. In this study, we propose a new network community detection-based approach to automatically label and classify text data into multiclass value spaces. Specifically, we build networks with sentences as the network nodes and pairwise cosine similarities between the Term Frequency-Inversed Document Frequency (TFIDF) vector representations of the sentences as the network link weights. We use the Louvain method to detect the communities in the sentence networks. We train and test the Support Vector Machine and the Random Forest models on both the human-labeled data and network community detection labeled data. Results showed that models with the data labeled by the network community detection outperformed the models with the human-labeled data by 2.68–3.75% of classification accuracy. Our method may help developments of more accurate conversational intelligence and other text classification systems.

Original languageEnglish
Title of host publicationProceedings of NetSci-X 2020
Subtitle of host publication6th International Winter School and Conference on Network Science
EditorsNaoki Masuda, Kwang-Il Goh, Tao Jia, Junichi Yamanoi, Hiroki Sayama
PublisherSpringer
Pages231-243
Number of pages13
ISBN (Print)9783030389642
DOIs
Publication statusPublished - 2020
Event6th International School and Conference on Network Science, NetSci-X 2020 - Tokyo, Japan
Duration: 2020 Jan 202020 Jan 23

Publication series

NameSpringer Proceedings in Complexity
ISSN (Print)2213-8684
ISSN (Electronic)2213-8692

Conference

Conference6th International School and Conference on Network Science, NetSci-X 2020
CountryJapan
CityTokyo
Period20/1/2020/1/23

Keywords

  • Artificial intelligence
  • Cosine similarity
  • Document networks
  • Machine learning
  • Natural language processing
  • Network community detection
  • Network science
  • Sentence networks
  • Text classification
  • TF-IDF
  • Topic modeling

ASJC Scopus subject areas

  • Applied Mathematics
  • Modelling and Simulation
  • Computer Science Applications

Fingerprint Dive into the research topics of 'The Power of Communities: A Text Classification Model with Automated Labeling Process Using Network Community Detection'. Together they form a unique fingerprint.

  • Cite this

    Kim, M., & Sayama, H. (2020). The Power of Communities: A Text Classification Model with Automated Labeling Process Using Network Community Detection. In N. Masuda, K-I. Goh, T. Jia, J. Yamanoi, & H. Sayama (Eds.), Proceedings of NetSci-X 2020: 6th International Winter School and Conference on Network Science (pp. 231-243). (Springer Proceedings in Complexity). Springer. https://doi.org/10.1007/978-3-030-38965-9_16