Multi-Task Ordinal Regression for Jointly Predicting the Trustworthiness and the Leading Political Ideology of News Media
This addresses the problem of detecting media bias and trustworthiness for combating fake news and propaganda, though it is incremental in applying multi-task learning to these specific tasks.
The paper tackles the joint prediction of news outlet trustworthiness (3-point scale) and political ideology (7-point scale) by proposing a multi-task ordinal regression framework, showing sizable performance gains over isolated models.
In the context of fake news, bias, and propaganda, we study two important but relatively under-explored problems: (i) trustworthiness estimation (on a 3-point scale) and (ii) political ideology detection (left/right bias on a 7-point scale) of entire news outlets, as opposed to evaluating individual articles. In particular, we propose a multi-task ordinal regression framework that models the two problems jointly. This is motivated by the observation that hyper-partisanship is often linked to low trustworthiness, e.g., appealing to emotions rather than sticking to the facts, while center media tend to be generally more impartial and trustworthy. We further use several auxiliary tasks, modeling centrality, hyperpartisanship, as well as left-vs.-right bias on a coarse-grained scale. The evaluation results show sizable performance gains by the joint models over models that target the problems in isolation.