Extending a Parliamentary Corpus with MPs' Tweets: Automatic Annotation and Evaluation Using MultiParTweet

TL;DR

This paper introduces MultiParTweet, a multilingual Twitter corpus linking politicians' social media discourse with parliamentary debates, enriched with automatic emotion, sentiment, and topic annotations, and evaluates the models' mutual predictability and alignment with human judgment.

Contribution

The paper presents MultiParTweet, a novel multilingual Twitter corpus with integrated automatic annotations and a framework for data collection, enabling comparative political discourse analysis.

Findings

Models can predict each other's outputs, indicating mutual predictability.

VLM-based annotations are preferred by human annotators, showing better alignment with human interpretation.

MultiParTweet is a validated resource for analyzing online political communication.

Abstract

Social media serves as a critical medium in modern politics because it both reflects politicians' ideologies and facilitates communication with younger generations. We present MultiParTweet, a multilingual tweet corpus from X that connects politicians' social media discourse with German political corpus GerParCor, thereby enabling comparative analyses between online communication and parliamentary debates. MultiParTweet contains 39 546 tweets, including 19 056 media items. Furthermore, we enriched the annotation with nine text-based models and one vision-language model (VLM) to annotate MultiParTweet with emotion, sentiment, and topic annotations. Moreover, the automated annotations are evaluated against a manually annotated subset. MultiParTweet can be reconstructed using our tool, TTLABTweetCrawler, which provides a framework for collecting data from X. To demonstrate a methodological demonstration, we examine whether the models can predict each other using the outputs of the remaining models. In summary, we provide MultiParTweet, a resource integrating automatic text and media-based annotations validated with human annotations, and TTLABTweetCrawler, a general-purpose X data collection tool. Our analysis shows that the models are mutually predictable. In addition, VLM-based annotation were preferred by human annotators, suggesting that multimodal representations align more with human interpretation.