Edinburgh Research Explorer

Using sequence constraints for modelling network interactions

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

Original languageEnglish
Title of host publicationAdvances in Artificial Intelligence
Subtitle of host publicationSelected Papers from the Annual Conference of Japanese Society of Artificial Intelligence (JSAI 2019)
EditorsY Ohsawa, K Yada, T Ito, Y Takama, E Sato-Shimokawara, A Abe, J Mori, N Matsumura
PublisherSpringer
Pages3-13
ISBN (Electronic)9783030398781
ISBN (Print)9783030398774
DOIs
Publication statusE-pub ahead of print - 4 Feb 2020

Publication series

NameAdvances in Intelligent Systems and Computing
PublisherSpringer
ISSN (Print)2194-5357

Abstract

This is an extension from a selected paper from JSAI2019. The ubiquitous nature of networks has led to a vast number of works dedicated to the study of capturing their information. Various graph-based techniques exist that report on the characteristics of nodes and edges, e.g., author-citation networks, social interactions, and so on. A significant amount of information can be extracted by summarizing the surrounding network structure of nodes, e.g., by capturing motives, or walk patterns. In this work, we present a new way of capturing the interaction between nodes in a network by making use of the sequence in which they occur. (1) The objective of this paper is to make use of behavioural constraint patterns; a concise but detailed report of node's interactions can be constructed that can be used for various purposes. (2) It is shown how the constraint patterns can be mined form interaction data, and how they can be used for various applications. (3) A case study is presented which uses behavioural constraint patterns to profile user interactions in a communication network.

    Research areas

  • sequence mining, network analysis

ID: 133429147