相关论文: Modeling Online Discourse with Coupled Distributed…

The relationship between crime and the media has long been a focal point of academic research, with traditional media playing a significant role in shaping public perceptions of safety and community well-being. However, the advent of social…

Large Language Models (LLMs) have recently emerged as powerful tools for natural language generation, with applications spanning from content creation to social simulations. Their ability to mimic human interactions raises both…

We introduce an approach to topic modelling with document-level covariates that remains tractable in the face of large text corpora. This is achieved by de-emphasizing the role of parameter estimation in an underlying probabilistic model,…

Understanding how people argue across ideological divides online is important for studying political polarization, misinformation, and content moderation. Existing datasets capture only part of this problem: some preserve text but ignore…

Recent advances in neural sequence-to-sequence models have led to promising results for several language generation-based tasks, including dialogue response generation, summarization, and machine translation. However, these models are known…

Statistical spoken dialogue systems usually rely on a single- or multi-domain dialogue model that is restricted in its capabilities of modelling complex dialogue structures, e.g., relations. In this work, we propose a novel dialogue model…

Neural network models are capable of generating extremely natural sounding conversational interactions. Nevertheless, these models have yet to demonstrate that they can incorporate content in the form of factual information or…

Online boards offer a platform for sharing and discussing content, where discussion emerges as a cascade of comments in response to a post. Branching point process models offer a practical approach to modelling these cascades; however,…

Representation shapes public attitudes and behaviors. With the recent advances and rapid adoption of LLMs, the way these systems are introduced will negotiate societal expectations for their role in high-stakes domains like health. Yet it…

We address the task of sentence retrieval for open-ended dialogues. The goal is to retrieve sentences from a document corpus that contain information useful for generating the next turn in a given dialogue. Prior work on dialogue-based…

During broadcast events such as the Superbowl, the U.S. Presidential and Primary debates, etc., Twitter has become the de facto platform for crowds to share perspectives and commentaries about them. Given an event and an associated…

Topic models are frequently used in machine learning owing to their high interpretability and modular structure. However, extending a topic model to include a supervisory signal, to incorporate pre-trained word embedding vectors and to…

Social groups are fundamental elements of any social system. Their emergence and evolution are closely related to the structure and dynamics of a social system. Research on social groups was primarily focused on the growth and the structure…

Inspired by e-participation systems, in this paper we propose a new model to represent human debates and methods to obtain collective conclusions from them. This model overcomes drawbacks of existing approaches by allowing users to…

Building robust and general dialogue models for spoken conversations is challenging due to the gap in distributions of spoken and written data. This paper presents our approach to build generalized models for the Knowledge-grounded…

Topic modeling is a well-established technique for exploring text corpora. Conventional topic models (e.g., LDA) represent topics as bags of words that often require "reading the tea leaves" to interpret; additionally, they offer users…

Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we develop the Embedded Topic…

Online social networks are a dominant medium in everyday life to stay in contact with friends and to share information. In Twitter, users can connect with other users by following them, who in turn can follow back. In recent years,…

Numerical interactions leading to users sharing textual content published by others are naturally represented by a network where the individuals are associated with the nodes and the exchanged texts with the edges. To understand those…

Urban transit agencies increasingly turn to social media to monitor emerging service risks such as crowding, delays, and safety incidents, yet the signals of concern are sparse, short, and easily drowned by routine chatter. We address this…