個人喜好在社群網路中傳播行為的預測

Abstract

一直以來，研究喜好如何在社群網路中擴散都是熱門課題。相較於過去往往視喜好為一個實數或單純的布林值，我們改採排名的方式解讀喜好，因而適用許多經典排序學習演算法以解決問題；但現實生活中囊括社群網路、時間以及喜好等完整資訊之數據取得不易，我們為此提出如何從各種數據內，間接提取所需訊息的替代方案。經實驗證明，在不同資料集上，本方法表現皆優於其他傳播模型。

This work tries to bring a marriage between two areas: social network analysis and machine learning, through the study of exploiting ranking-based learning models for preference prediction on social networks. The diffusion of information on social networks has been studied for decades. This paper proposes a study of the diffusion of human preference on social networks, which is a novel problem to solve in this direction. In general, there are two types of approaches proposed to predict the diffusion of information on networks: the model-driven and data-driven approaches. The former assumes an underlying mechanism for diffusion, and the later tries to learn a more flexible model given data. This paper first proposes a simple modification on the existing model-driven binary diffusion approaches for preference list diffusion, and then addresses some concerns by proposing a rank-learning based data-driven approach. To evaluate the approaches, we propose two scenarios which data can be obtained from publicly available sources: the citation behavior and the microblogging behavior changes. The experiments show that the proposed ranking-based data-driven method outperforms all the other competitors significantly in both evaluation scenarios.