SBSOM : Self-Organizing Map for Visualizing Structure in the Time Series of Hot Topics(Text Mining I)(Joint Workshop of Vietnamese Society of AI, SIGKBS-JSAI, ICS-IPSJ, and IEICE-SIGAI on Active Mining)
スポンサーリンク
概要
- 論文の詳細を見る
In this paper, we propose a Sequence-Based Self-Organizing Map (SBSOM) that organizes clusters as series within the map to visualize their structure in terms of hotness, period and relations among topics. Principal Component Analysis (PCA) that is based on probabilistic document generation model is applied to extract hot topics from vast amount of documents, and these hot topics are used to label each document. Afterwhich, SBSOM is used to visualize these hot topics in a time series. SBSOM is also extended by defining label confidence for a more accurate labeling of its neurons. The initial experiments that use two kinds of. News articles, the largest expands across ten years, validate that in addition to SOM showing only hotness of topics and relations among topics throughout whole period, SBSOM shows hotness within certain times, relations among topics, and period of topics.
- 2004-11-27
著者
-
FUKUI KEN-ICHI
Dept. of Information Science and Technology, Osaka University
-
SAITO KAZUMI
NTT Communication Science Laboratories
-
KIMURA MASAHIRO
NTT Communication Science Laboratories
-
NUMAO MASAYUKI
The Institute of Scientific and Industrial Research, Osaka University
-
Numao Masayuki
The Institute Of Scientific And Industrial Research Osaka University
-
Fukui Ken-ichi
Dept. Of Information Science And Technology Osaka University
-
Kimura M
Ntt Communication Science Laboratories
関連論文
- SBSOM : Self-Organizing Map for Visualizing Structure in the Time Series of Hot Topics(Text Mining I)
- SBSOM : Self-Organizing Map for Visualizing Structure in the Time Series of Hot Topics(Text Mining I)(Joint Workshop of Vietnamese Society of AI, SIGKBS-JSAI, ICS-IPSJ, and IEICE-SIGAI on Active Mining)
- Extracting Communities from Complex Networks by the k-Dense Method
- Visualization of Damage Progress in Solid Oxide Fuel Cells
- Kinetic Evaluation and Characterization of Ceramic Honeycomb-Monolith Bioreactor
- Inductive Logic Programming for Multiple-Part Data : Applications on Structure-Activity Relationship Studies
- Partial Rule Weighting Using Single-Layer Perceptron(Artificial Intelligence III)
- Multiple-Instance Learning Based Heuristics for Mining Chemical Compound Structure(Scientific Data Mining)
- Partial Rule Weighting Using Single-Layer Perceptron(Artificial Intelligence III)(Joint Workshop of Vietnamese Society of AI, SIGKBS-JSAI, ICS-IPSJ, and IEICE-SIGAI on Active Mining)
- Multiple-Instance Learning Based Heuristics for Mining Chemical Compound Structure(Scientific Data Mining)(Joint Workshop of Vietnamese Society of AI, SIGKBS-JSAI, ICS-IPSJ, and IEICE-SIGAI on Active Mining)
- A Category-based Framework of a Self-improving Instructional Planner
- Extracting regression rules from neural networks
- Modeling of growing networks with directional attachment and communities
- Feature Discovery in Temporal Data(Artificial Intelligence III)
- Preprocessing Planning for Data Mining(Artificial Intelligence I)
- Preprocessing Planning for Data Mining(Artificial Intelligence I)(Joint Workshop of Vietnamese Society of AI, SIGKBS-JSAI, ICS-IPSJ, and IEICE-SIGAI on Active Mining)
- Feature Discovery in Temporal Data(Artificial Intelligence III)(Joint Workshop of Vietnamese Society of AI, SIGKBS-JSAI, ICS-IPSJ, and IEICE-SIGAI on Active Mining)
- A Category-based Framework of a Self-improving Instructional Planner