Saket Sharma, Aviral Joshi, Yiyun Zhao, Namrata Mukhija, Hanoz Bhathena, Prateek Singh, Sashank Santhanam. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Social engineers attempt to manipulate users into undertaking actions such as downloading malware by clicking links or providing access to money or sensitive information. Natural language processing, computational sociolinguistics, and media-specific structural clues provide a means for detecting both the ask (e.g., buy gift card) and the risk/reward implied by the ask, which we call framing (e.g., lose your job, get a raise). We apply linguistic resources such as Lexical Conceptual Structure to tackle ask detection and also leverage structural clues such as links and their proximity to identified asks to improve confidence in our results. Our experiments indicate that the performance of ask detection, framing detection, and identification of the top ask is improved by linguistically motivated classes coupled with structural clues such as links. Our approach is implemented in a system that informs users about social engineering risk situations.

Humans quite frequently interact with conversational agents. The rapid advancement in generative language modeling through neural networks has helped advance the creation of intelligent conversational agents. Researchers typically evaluate the output of their models through crowdsourced judgments, but there are no established best practices for conducting such studies. Moreover, it is unclear if cognitive biases in decision-making are affecting crowdsourced workers' judgments when they undertake these tasks. To investigate, we conducted a between-subjects study with 77 crowdsourced workers to understand the role of cognitive biases, specifically anchoring bias, when humans are asked to evaluate the output of conversational agents. Our results provide insight into how best to evaluate conversational agents. We find increased consistency in ratings across two experimental conditions may be a result of anchoring bias. We also determine that external factors such as time and prior experience in similar tasks have effects on inter-rater consistency.

David M. Howcroft, Anya Belz, Miruna-Adriana Clinciu, Dimitra Gkatzia, Sadid A. Hasan, Saad Mahamood, Simon Mille, Emiel van Miltenburg, Sashank Santhanam, Verena Rieser. Proceedings of the 13th International Conference on Natural Language Generation. 2020.

To overcome the limitations of automated metrics (e.g.BLEU, METEOR) for evaluating dialogue systems, researchers typically use human judgments to provide convergent evidence.While it has been demonstrated that human judgments can suffer from the inconsistency of ratings, extant research has also found that the design of the evaluation task affects the consistency and quality of human judgments.We conduct a between-subjects study to understand the impact of four experiment conditions on human ratings of dialogue system output.In addition to discrete and continuous scale ratings, we also experiment with a novel application of Best-Worst scaling to dialogue evaluation.Through our systematic study with 40 crowdsourced workers in each task, we find that using continuous scales achieves more consistent ratings than Likert scale or ranking-based experiment design.Additionally, we find that factors such as time taken to complete the task and no prior experience of participating in similar studies of rating dialogue system output positively impact consistency and agreement amongst raters.

We present Verifi2, a visual analytic system to support the investigation of misinformation on social media. Various models and studies have emerged from multiple disciplines to detect or understand the effects of misinformation. However, there is still a lack of intuitive and accessible tools that help social media users distinguish misinformation from verified news. Verifi2 uses state-of-the-art computational methods to highlight linguistic, network, and image features that can distinguish suspicious news accounts. By exploring news on a source and document level in Verifi2, users can interact with the complex dimensions that characterize misinformation and contrast how real and suspicious news outlets differ on these dimensions. To evaluate Verifi2, we conduct interviews with experts in digital media, communications, education, and psychology who study misinformation. Our interviews highlight the complexity of the problem of combating misinformation and show promising potential for Verifi2 as an educational tool on misinformation.

Abstract Cognitive biases are systematic errors in judgment due to an over‐reliance on rule‐of‐thumb heuristics. Recent research suggests that cognitive biases, like numerical anchoring, transfers to visual analytics in the form of visual anchoring. However, it is unclear how visualization users can be visually anchored and how the anchors affect decision‐making. To investigate, we performed a between‐subjects laboratory experiment with 94 participants to analyze the effects of visual anchors and strategy cues using a visual analytics system. The decision‐making task was to identify misinformation from Twitter news accounts. Participants were randomly assigned to conditions that modified the scenario video (visual anchor) and/or strategy cues provided. Our findings suggest that such interventions affect user activity, speed, confidence, and, under certain circumstances, accuracy. We discuss implications of our results on the forking paths problem and raise concerns on how visualization researchers train users to avoid unintentionally anchoring users and affecting the end result.