Related papers: VIBE: Topic-Driven Temporal Adaptation for Twitter…
Social media are becoming an increasingly important source of information about the public mood regarding issues such as elections, Brexit, stock market, etc. In this paper we focus on sentiment classification of Twitter data. Construction…
Recent progress in language model pre-training has led to important improvements in Named Entity Recognition (NER). Nonetheless, this progress has been mainly tested in well-formatted documents such as news, Wikipedia, or scientific…
Information spread in social media depends on a number of factors, including how the site displays information, how users navigate it to find items of interest, users' tastes, and the `virality' of information, i.e., its propensity to be…
Social media platforms host discussions about a wide variety of topics that arise everyday. Making sense of all the content and organising it into categories is an arduous task. A common way to deal with this issue is relying on topic…
Nowadays, topic classification from tweets attracts considerable research attention. Different classification systems have been suggested thanks to these research efforts. Nevertheless, they face major challenges owing to low performance…
Machine learning models benefit when allowed to learn from temporal trends in time-stamped administrative data. These trends can be represented by dividing a model's observation window into time segments or bins. Model training time and…
Large Audio-Language Models (LALMs) are increasingly integrated into daily applications, yet their generative biases remain underexplored. Existing speech fairness benchmarks rely on synthetic speech and Multiple-Choice Questions (MCQs),…
Current models for predicting social media virality rely heavily on static textual and structural features, effectively ignoring the highly dynamic nature of trend signals. We study whether real-world attention signals can improve the…
Domain adaptation aims to leverage the supervision signal of source domain to obtain an accurate model for target domain, where the labels are not available. To leverage and adapt the label information from source domain, most existing…
The rise in popularity and ubiquity of Twitter has made sentiment analysis of tweets an important and well-covered area of research. However, the 140 character limit imposed on tweets makes it hard to use standard linguistic methods for…
This paper presents Hyper-VIB, a hypernetwork-enhanced information bottleneck (IB) approach designed to enable efficient task-oriented communications in 6G collaborative intelligent systems. Leveraging IB theory, our approach enables an…
In this paper we shed light on the impact of fine-tuning over social media data in the internal representations of neural language models. We focus on bot detection in Twitter, a key task to mitigate and counteract the automatic spreading…
We propose a method to discover latent topics and visualise large collections of tweets for easy identification and interpretation of topics, and exemplify its use with tweets from a Colombian mass media giant in the period 2014--2019. The…
This study investigates the challenges posed by the dynamic nature of legal multi-label text classification tasks, where legal concepts evolve over time. Existing models often overlook the temporal dimension in their training process,…
Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts in representation…
Toxicity is pervasive in social media and poses a major threat to the health of online communities. The recent introduction of pre-trained language models, which have achieved state-of-the-art results in many NLP tasks, has transformed the…
Relational databases underpin critical infrastructure across a wide range of domains, yet the design of generalizable pre-training strategies for learning from relational databases remains an open challenge due to task heterogeneity.…
In this paper, we explore the visual representations produced from a pre-trained text-to-video (T2V) diffusion model for video understanding tasks. We hypothesize that the latent representation learned from a pretrained generative T2V model…
We tackle the challenge of topic classification of tweets in the context of analyzing a large collection of curated streams by news outlets and other organizations to deliver relevant content to users. Our approach is novel in applying…
Topic models and all their variants analyse text by learning meaningful representations through word co-occurrences. As pointed out by Williamson et al. (2010), such models implicitly assume that the probability of a topic to be active and…