Forecasting Social Networks Utilizing Mutual Effects of Friendship and Their Interests

2022 Fiscal Year Final Research Report

• Project/Area Number: 20K23337
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Multi-year Fund
• Review Section: 1002:Human informatics, applied informatics and related fields
• Research Institution: University of Tsukuba
• Principal Investigator: Ito Hiroyoshi 筑波大学, 図書館情報メディア系, 助教 (90875741)
• Project Period (FY): 2020-09-11 – 2023-03-31
• Keywords: 時系列データ解析 / グラフデータマイニング / 機械学習 / ソーシャルネットワーク予測

Outline of Final Research Achievements

The objective of this study is to devise mathematical models capable of long-term prediction of changes in social networks. Throughout this study, efforts were primarily directed toward: (1) developing prediction models based on the modeling of the mutual effects between changes in human relationships and shifts in interests; (2) creating interpretable prediction models based on the modeling of individuals' reward functions and behavioral strategies within the network. In each research, we empirically demonstrated the achievement of predictive accuracy surpassing existing models and the ability to generate predictive results that are interpretable to humans.

Free Research Field

データマイニング

Academic Significance and Societal Importance of the Research Achievements

本研究が対象とするソーシャルネットワークは，SNSにおけるユーザの友人関係や，研究者間の共著ネットワークなど多様なデータを表現可能であり，ソーシャルネットワークの変化を予測することで，友人関係の変化，各人の興味関心の変化が予測可能になる．SNSの普及に伴い，ソーシャルネットワーク分析による価値創造への需要が高まる中，このような予測ができることで，コンテンツに対してどれだけの人が関心を抱くかを予測することによるマーケティングへの活用や，社会動向の変化の予測に応用可能である．