Meiqi Guo


2022

pdf bib
ImageArg: A Multi-modal Tweet Dataset for Image Persuasiveness Mining
Zhexiong Liu | Meiqi Guo | Yue Dai | Diane Litman
Proceedings of the 9th Workshop on Argument Mining

The growing interest in developing corpora of persuasive texts has promoted applications in automated systems, e.g., debating and essay scoring systems; however, there is little prior work mining image persuasiveness from an argumentative perspective. To expand persuasiveness mining into a multi-modal realm, we present a multi-modal dataset, ImageArg, consisting of annotations of image persuasiveness in tweets. The annotations are based on a persuasion taxonomy we developed to explore image functionalities and the means of persuasion. We benchmark image persuasiveness tasks on ImageArg using widely-used multi-modal learning methods. The experimental results show that our dataset offers a useful resource for this rich and challenging topic, and there is ample room for modeling improvement.

2020

pdf
Inflating Topic Relevance with Ideology: A Case Study of Political Ideology Bias in Social Topic Detection Models
Meiqi Guo | Rebecca Hwa | Yu-Ru Lin | Wen-Ting Chung
Proceedings of the 28th International Conference on Computational Linguistics

We investigate the impact of political ideology biases in training data. Through a set of comparison studies, we examine the propagation of biases in several widely-used NLP models and its effect on the overall retrieval accuracy. Our work highlights the susceptibility of large, complex models to propagating the biases from human-selected input, which may lead to a deterioration of retrieval accuracy, and the importance of controlling for these biases. Finally, as a way to mitigate the bias, we propose to learn a text representation that is invariant to political ideology while still judging topic relevance.