The Generation of Cluster Labels Based on Cluster Analysis for MMORPG Game

  • Cha, You Na
  • Lee, Won Hyung
  • Park, Sang Yong

초록

characteristics at MMORPG Game, how to provide these users with efficient, safe, and personalized network services is a problem that needs to be solved urgently. The clustering algorithm needs to pre-determine the scale of user behavior data when analyzing network user behavior, and the generated clusters also lack semantic features. Therefore, this paper conducts cluster analysis on the characteristics of network user behavior data, and applies LFM, matrix decomposition and other methods to propose an automatic cluster label generation method for network user behavior clustering. The experimental results show that the proposed method does not need to determine the scale of user behavior data in advance, and cluster labels can be generated at the same time in the clustering process, and the generated cluster labels conform to the actual semantics of user behavior.

키워드

user groupuser behaviorclustering algorithmmatrix decompositionlatent factor model
제목
The Generation of Cluster Labels Based on Cluster Analysis for MMORPG Game
저자
Cha, You NaLee, Won HyungPark, Sang Yong
DOI
10.22819/kscg.2022.35.2.008
발행일
2022-06
저널명
한국컴퓨터게임학회논문지
35
2
페이지
67 ~ 77