[论文解读] Ideology Detection for Twitter Users with Heterogeneous Types of Links
本文提出 ML-IPM,一种统一的概率模型,通过整合异构链接类型(关注、提及、转发)来检测 Twitter 用户的连续意识形态立场,同时自动学习每种链接类型的相对重要性。该模型在意识形态排序和分类任务中优于基线方法,尤其在连接稀疏的用户中表现更优,且与人类直觉高度一致。
The problem of ideology detection is to study the latent (political) placement for people, which is traditionally studied on politicians according to their voting behaviors. Recently, more and more studies begin to address the ideology detection problem for ordinary users based on their online behaviors that can be captured by social media, e.g., Twitter. As far as we are concerned, however, the vast majority of the existing methods on ideology detection on social media have oversimplified the problem as a binary classification problem (i.e., liberal vs. conservative). Moreover, though social links can play a critical role in deciding one's ideology, most of the existing work ignores the heterogeneous types of links in social media. In this paper we propose to detect \emph{numerical} ideology positions for Twitter users, according to their \emph{follow}, \emph{mention}, and \emph{retweet} links to a selected set of politicians. A unified probabilistic model is proposed that can (1) explain the reasons why links are built among people in terms of their ideology, (2) integrate heterogeneous types of links together in determining people's ideology, and (3) automatically learn the quality of each type of links in deciding one's ideology. Experiments have demonstrated the advantages of our model in terms of both ranking and political leaning classification accuracy. It is shown that (1) using multiple types of links is better than using any single type of links alone to determine one's ideology, and (2) our model is even more superior than baselines when dealing with people that are sparsely linked in one type of links. We also show that the detected ideology for Twitter users aligns with our intuition quite well.
研究动机与目标
- 解决现有意识形态检测方法将政治立场简化为二元分类(自由派 vs. 保守派)的局限性。
- 对社交媒体链接的异质性(关注、提及、转发)进行建模,而非将其视为同质或忽略类型差异。
- 自动学习每种链接类型在预测意识形态中的相对强度,避免手动或启发式赋权。
- 提升意识形态估计的准确性,尤其针对在任一链接类型中连接稀疏的用户。
- 提供连续的、实值的理想点估计,反映政治意识形态的完整光谱,而非仅限于二元类别。
提出的方法
- 该模型基于社会选择理论,解释链接形成基于意识形态相似性,将链接存在的概率建模为用户理想点的函数。
- 提出一种统一的概率框架,联合估计用户理想点以及每种链接类型在意识形态推断中的相对影响(权重)。
- 通过基于可扩展期望最大化(EM)的算法学习链接类型权重,以优化观测网络数据的似然函数。
- 将多种链接类型(关注、提及、转发)整合到单一概率图中,实现跨类型的信息传递。
- 通过在不同类型间转移知识来应对网络稀疏性问题,提升在任一类型中连接有限用户的性能。
- 采用潜在变量表示用户意识形态,估计一维空间中的连续理想点。
实验结果
研究问题
- RQ1统一模型能否有效整合多种异构链接类型(关注、提及、转发),以超越单一类型链接分析,提升意识形态检测性能?
- RQ2该模型自动学习链接类型权重的能力与固定或人工调优权重相比,在意识形态估计中表现如何?
- RQ3该模型在仅在单一链接类型中连接稀疏的用户上是否仍能保持或提升性能?
- RQ4检测到的意识形态在多大程度上与人类直觉以及公众人物的已知政治立场一致?
- RQ5该模型能否在排序和分类任务中均优于现有的二元分类或单链接类型方法?
主要发现
- 使用多种异构链接类型显著提升了意识形态检测性能,相比单独使用任一类型均有明显提升。
- 所提出的 ML-IPM 模型在政治倾向分类任务中的准确率高于所有基线方法,尤其在连接稀疏的用户中表现更优。
- 通过利用跨链接类型的信息传递,该模型在连接稀疏用户中表现出色,有效缓解了冷启动问题。
- 自动学习到的链接类型权重符合现实直觉——例如,转发比关注对意识形态推断更具信息量。
- 案例研究显示,检测到的理想点与公众人物的已知政治立场高度一致,例如 Rachel Maddow 的意识形态倾向比 Anderson Cooper 更为自由。
- 该模型能基于转发行为成功区分具有相似关注模式但意识形态迥异的用户,例如 Glenn Greenwald 与 Megyn Kelly。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。