Search for: All records

With the spread of the SARS-CoV-2, enormous amounts of information about the pandemic are disseminated through social media platforms such as Twitter. Social media posts often leverage the trust readers have in prestigious news agencies and cite news articles as a way of gaining credibility. Nevertheless, it is not always the case that the cited article supports the claim made in the social media post. We present a cross-genre ad hoc pipeline to identify whether the information in a Twitter post (i.e., a “Tweet”) is indeed supported by the cited news article. Our approach is empirically based on a corpus of over 46.86 million Tweets and is divided into two tasks: (i) development of models to detect Tweets containing claim and worth to be fact-checked and (ii) verifying whether the claims made in a Tweet are supported by the newswire article it cites. Unlike previous studies that detect unsubstantiated information by post hoc analysis of the patterns of propagation, we seek to identify reliable support (or the lack of it) before the misinformation begins to spread. We discover that nearly half of the Tweets (43.4%) are not factual and hence not worth checking – a significant filter, given the sheer volume of social media posts on a platform such as Twitter. Moreover, we find that among the Tweets that contain a seemingly factual claim while citing a news article as supporting evidence, at least 1% are not actually supported by the cited news, and are hence misleading. 

In natural language understanding, topics that touch upon figurative language and pragmatics are notably difficult. We probe a novel use of locally aggregated descriptors -- specifically, an architecture called NeXtVLAD -- motivated by its accomplishments in computer vision, achieve tremendous success in the FigLang2020 sarcasm detection task. The reported F1 score of 93.1% is 14% higher than the next best result. We specifically investigate the extent to which the novel architecture is responsible for this boost, and find that it does not provide statistically significant benefits. Deep learning approaches are expensive, and we hope our insights highlighting the lack of benefits from introducing a resource-intensive component will aid future research to distill the effective elements from long and complex pipelines, thereby providing a boost to the wider research community. 

The explosion of online health news articles runs the risk of the proliferation of low-quality information. Within the existing work on fact-checking, however, relatively little attention has been paid to medical news. We present a health news classification task to determine whether medical news articles satisfy a set of review criteria deemed important by medical experts and health care journalists. We present a dataset of 1,119 health news paired with systematic reviews. The review criteria consist of six elements that are essential to the accuracy of medical news. We then present experiments comparing the classical token-based approach with the more recent transformer-based models. Our results show that detecting qualitative lapses is a challenging task with direct ramifications in misinformation, but is an important direction to pursue beyond assigning True or False labels to short claims. 

We present a query-based biomedical information retrieval task across two vastly different genres -- newswire and research literature -- where the goal is to find the research publication that supports the primary claim made in a health-related news article. For this task, we present a new dataset of 5,034 claims from news paired with research abstracts. Our approach consists of two steps: (i) selecting the most relevant candidates from a collection of 222k research abstracts, and (ii) re-ranking this list. We compare the classical IR approach using BM25 with more recent transformer-based models. Our results show that cross-genre medical IR is a viable task, but incorporating domain-specific knowledge is crucial. 

As the spread of information has received a compelling boost due to pervasive use of social media, so has the spread of misinformation. The sheer volume of data has rendered the traditional methods of expert-driven manual fact-checking largely infeasible. As a result, computational linguistics and data-driven algorithms have been explored in recent years. Despite this progress, identifying and prioritizing what needs to be checked has received little attention. Given that expert-driven manual intervention is likely to remain an important component of fact-checking, especially in specific domains (e.g., politics, environmental science), this identification and prioritization is critical. A successful algorithmic ranking of “check-worthy” claims can help an expert-in-the-loop fact-checking system, thereby reducing the expert’s workload while still tackling the most salient bits of misinformation. In this work, we explore how linguistic syntax, semantics, and the contextual meaning of words play a role in determining the check-worthiness of claims. Our preliminary experiments used explicit stylometric features and simple word embeddings on the English language dataset in the Check-worthiness task of the CLEF-2018 Fact-Checking Lab, where our primary solution outperformed the other systems in terms of the mean average precision, R-precision, reciprocal rank, and precision at k for multiple values k. Here, we present an extension of this approach with more sophisticated word embeddings and report further improvements in this task. 

In recent years, the speed at which information disseminates has received an alarming boost from the pervasive usage of social media. To the detriment of political and social stability, this has also made it easier to quickly spread false claims. Due to the sheer volume of information, manual fact-checking seems infeasible, and as a result, computational approaches have been recently explored for automated fact-checking. In spite of the recent advancements in this direction, the critical step of recognizing and prioritizing statements worth fact-checking has received little attention. In this paper, we propose a hybrid approach that combines simple heuristics with supervised machine learning to identify claims made in political debates and speeches, and provide a mechanism to rank them in terms of their "check-worthiness". The viability of our method is demonstrated by evaluations on the English language dataset as part of the Check-worthiness task of the CLEF-2018 Fact Checking Lab.