Multi-grain hierarchical topic extraction algorithm for text mining
Expert Systems with Applications: An International Journal
The possibility of an epidemic meme analogy for web community population analysis
IDEAL'07 Proceedings of the 8th international conference on Intelligent data engineering and automated learning
Population estimation of internet forum community by posted article distribution
KES'10 Proceedings of the 14th international conference on Knowledge-based and intelligent information and engineering systems: Part IV
Word familiarity distributions to understand heaps' law of vocabulary growth of the internet forums
KES'11 Proceedings of the 15th international conference on Knowledge-based and intelligent information and engineering systems - Volume Part III
| Hi-index | 0.00 |
The objective of this paper is to understand an aspect of human social interaction in public bulletin board systems (BBSs). We try to answer the question of why and how a long and hot chain of articles often emerges in BBSs. This paper presents the following three contributions. (1) Empirical results: we measured and analyzed actual BBS logs, and found that the number of articles submitted by each individual in an article chain follows a lognormal distribution. (2) Model: to investigate why the distribution emerges through individual activities, we developed a simple model of voluntary submission activity for each individual. With only this simple mechanism, the lognormal distribution shown in actual data is reproduced. (3) Analytical solution: we showed that the model generates a lognormal distribution when the number of members in a BBS community is constant, and the individuals in a community are homogeneous.