arXiv subjects

Simon T. Perrault

Publications and source records attributed to Simon T. Perrault.

15 recordsLinked to original sources

arXiv2025

Sword and Shield: Uses and Strategies of LLMs in Navigating Disinformation

The emergence of Large Language Models (LLMs) presents a dual challenge in the fight against disinformation. These powerful tools, capable of generating human-like text at scale, can be weaponised to produce sophisticated and persuasive disinformation, yet they also hold promise for enhancing detection and mitigation strategies. This paper investigates the complex dynamics between LLMs and disinformation through a communication game that simulates online forums, inspired by the game Werewolf, with 25 participants. We analyse how Disinformers, Moderators, and Users leverage LLMs to advance their goals, revealing both the potential for misuse and combating disinformation. Our findings highlight the varying uses of LLMs depending on the participants' roles and strategies, underscoring the importance of understanding their effectiveness in this context. We conclude by discussing implications for future LLM development and online platform design, advocating for a balanced approach that empowers users and fosters trust while mitigating the risks of LLM-assisted disinformation.

cs.HC↗

arXiv2025

Iffy-Or-Not: Extending the Web to Support the Critical Evaluation of Fallacious Texts

Social platforms have expanded opportunities for deliberation with the comments being used to inform one's opinion. However, using such information to form opinions is challenged by unsubstantiated or false content. To enhance the quality of opinion formation and potentially confer resistance to misinformation, we developed Iffy-Or-Not (ION), a browser extension that seeks to invoke critical thinking when reading texts. With three features guided by argumentation theory, ION highlights fallacious content, suggests diverse queries to probe them with, and offers deeper questions to consider and chat with others about. From a user study (N=18), we found that ION encourages users to be more attentive to the content, suggests queries that align with or are preferable to their own, and poses thought-provoking questions that expands their perspectives. However, some participants expressed aversion to ION due to misalignments with their information goals and thinking predispositions. Potential backfiring effects with ION are discussed.

cs.HC↗

arXiv2024

XAI in Automated Fact-Checking? The Benefits Are Modest and There's No One-Explanation-Fits-All

The massive volume of online information along with the issue of misinformation has spurred active research in the automation of fact-checking. Like fact-checking by human experts, it is not enough for an automated fact-checker to just be accurate, but also be able to inform and convince the user of the validity of its predictions. This becomes viable with explainable artificial intelligence (XAI). In this work, we conduct a study of XAI fact-checkers involving 180 participants to determine how users' actions towards news and their attitudes towards explanations are affected by the XAI. Our results suggest that XAI has limited effects on users' agreement with the veracity prediction of the automated fact-checker and on their intent to share news. However, XAI nudges users towards forming uniform judgments of news veracity, thereby signaling their reliance on the explanations. We also found polarizing preferences towards XAI and raise several design considerations on them.

cs.HC↗

arXiv2024

Evaluation of an LLM in Identifying Logical Fallacies: A Call for Rigor When Adopting LLMs in HCI Research

There is increasing interest in the adoption of LLMs in HCI research. However, LLMs may often be regarded as a panacea because of their powerful capabilities with an accompanying oversight on whether they are suitable for their intended tasks. We contend that LLMs should be adopted in a critical manner following rigorous evaluation. Accordingly, we present the evaluation of an LLM in identifying logical fallacies that will form part of a digital misinformation intervention. By comparing to a labeled dataset, we found that GPT-4 achieves an accuracy of 0.79, and for our intended use case that excludes invalid or unidentified instances, an accuracy of 0.90. This gives us the confidence to proceed with the application of the LLM while keeping in mind the areas where it still falls short. The paper describes our evaluation approach, results and reflections on the use of the LLM for our intended task.

cs.HC↗

arXiv2024

Local Perceptions and Practices of News Sharing and Fake News

Fake news is a prevalent problem, particularly in digital media, that undermines trust and cooperation among people. As a variety of global mitigation efforts arise, the understanding of how people consider fake news becomes important, especially in local contexts. To that end, we carried out a survey with 75 participants in Singapore to understand people's perceptions of and practices with news (real and fake). Locally, fake news was found to be more pervasive in instant messaging apps than in social media, with the problem attributed more strongly to sharing than to creation. Good news sharing practices were generally observed. Highest trust was reported in government communication platforms across 11 media items. These results show that Singapore possesses a peculiar sociocultural scene, suggesting that efforts directed towards locally relevant measures may be more effective in addressing fake news in Singapore. We detail the survey results and recommended directions in this paper.

cs.HC↗

arXiv2024

Rapid AIdeation: Generating Ideas With the Self and in Collaboration With Large Language Models

Generative artificial intelligence (GenAI) can rapidly produce large and diverse volumes of content. This lends to it a quality of creativity which can be empowering in the early stages of design. In seeking to understand how creative ways to address practical issues can be conceived between humans and GenAI, we conducted a rapid ideation workshop with 21 participants where they used a large language model (LLM) to brainstorm potential solutions and evaluate them. We found that the LLM produced a greater variety of ideas that were of high quality, though not necessarily of higher quality than human-generated ideas. Participants typically prompted in a straightforward manner with concise instructions. We also observed two collaborative dynamics with the LLM fulfilling a consulting role or an assisting role depending on the goals of the users. Notably, we observed an atypical anti-collaboration dynamic where participants used an antagonistic approach to prompt the LLM.

cs.HC↗

arXiv2024

Fact Checking Chatbot: A Misinformation Intervention for Instant Messaging Apps and an Analysis of Trust in the Fact Checkers

In Singapore, there has been a rise in misinformation on mobile instant messaging services (MIMS). MIMS support both small peer-to-peer networks and large groups. Misinformation in the former may spread due to recipients' trust in the sender while in the latter, misinformation can directly reach a wide audience. The encryption of MIMS makes it difficult to address misinformation directly. As such, chatbots have become an alternative solution where users can disclose their chat content directly to fact checking services. To understand how effective fact checking chatbots are as an intervention and how trust in three different fact checkers (i.e., Government, News Outlets, and Artificial Intelligence) may affect this trust, we conducted a within-subjects experiment with 527 Singapore residents. We found mixed results for the fact checkers but support for the chatbot intervention overall. We also found a striking contradiction between participants' trust in the fact checkers and their behaviour towards them. Specifically, those who reported a high level of trust in the government performed worse and tended to follow the fact checking tool less when it was endorsed by the government.

cs.HC↗

arXiv2024

Effects of Automated Misinformation Warning Labels on the Intents to Like, Comment and Share Posts

With fact-checking by professionals being difficult to scale on social media, algorithmic techniques have been considered. However, it is uncertain how the public may react to labels by automated fact-checkers. In this study, we investigate the use of automated warning labels derived from misinformation detection literature and investigate their effects on three forms of post engagement. Focusing on political posts, we also consider how partisanship affects engagement. In a two-phases within-subjects experiment with 200 participants, we found that the generic warnings suppressed intents to comment on and share posts, but not on the intent to like them. Furthermore, when different reasons for the labels were provided, their effects on post engagement were inconsistent, suggesting that the reasons could have undesirably motivated engagement instead. Partisanship effects were observed across the labels with higher engagement for politically congruent posts. We discuss the implications on the design and use of automated warning labels.

cs.HC↗

arXiv2023

Effectiveness of Area-to-Value Legends and Grid Lines in Contiguous Area Cartograms

A contiguous area cartogram is a geographic map in which the area of each region is proportional to numerical data (e.g., population size) while keeping neighboring regions connected. In this study, we investigated whether value-to-area legends (square symbols next to the values represented by the squares' areas) and grid lines aid map readers in making better area judgments. We conducted an experiment to determine the accuracy, speed, and confidence with which readers infer numerical data values for the mapped regions. We found that, when only informed about the total numerical value represented by the whole cartogram without any legend, the distribution of estimates for individual regions was centered near the true value with substantial spread. Legends with grid lines significantly reduced the spread but led to a tendency to underestimate the values. Comparing differences between regions or between cartograms revealed that legends and grid lines slowed the estimation without improving accuracy. However, participants were more likely to complete the tasks when legends and grid lines were present, particularly when the area units represented by these features could be interactively selected. We recommend considering the cartogram's use case and purpose before deciding whether to include grid lines or an interactive legend.

cs.HC↗

arXiv2020

Task-Based Effectiveness of Interactive Contiguous Area Cartograms

Cartograms are map-based data visualizations in which the area of each map region is proportional to an associated numeric data value (e.g., population or gross domestic product). A cartogram is called contiguous if it conforms to this area principle while also keeping neighboring regions connected. Because of their distorted appearance, contiguous cartograms have been criticized as difficult to read. Some authors have suggested that cartograms may be more legible if they are accompanied by interactive features (e.g., animations, linked brushing, or infotips). We conducted an experiment to evaluate this claim. Participants had to perform visual analysis tasks with interactive and noninteractive contiguous cartograms. The task types covered various aspects of cartogram readability, ranging from elementary lookup tasks to synoptic tasks (i.e., tasks in which participants had to summarize high-level differences between two cartograms). Elementary tasks were carried out equally well with and without interactivity. Synoptic tasks, by contrast, were more difficult without interactive features. With access to interactivity, however, most participants answered even synoptic questions correctly. In a subsequent survey, participants rated the interactive features as "easy to use" and "helpful." Our study suggests that interactivity has the potential to make contiguous cartograms accessible even for those readers who are unfamiliar with interactive computer graphics or do not have a prior affinity to working with maps. Among the interactive features, animations had the strongest positive effect, so we recommend them as a minimum of interactivity when contiguous cartograms are displayed on a computer screen.

cs.HC↗

arXiv2020

Pose Estimation for Facilitating Movement Learning from Online Videos

There exists a multitude of online video tutorials to teach physical movements such as exercises. Yet, users lack support to verify the accuracy of their movements when following such videos and have to rely on their own perception. To address this, we developed a web-based application that performs human pose estimation using both video inputs from the online video and web camera, then provides different types of visual feedback to a user. Our study suggests that the user's skeleton overlaid on the user's camera feed improved user performance, whereas the user's skeleton on its own or trainer's skeleton with the trainer video offered limited benefits. We believe that our application demonstrates the potential to enhance learning physical movements from online videos and provides a basis for other guidance systems to design suitable visualizations.

cs.HC↗

arXiv2020

Vibrotactile Feedback for Vertical 2D Space Exploration

Visually impaired people encounter many challenges in their everyday life, especially when it comes to navigating and representing space. The issue of shopping is addressed mostly on the level of navigation and product detection, but conveying clues about the object position to the user is rarely implemented. This work presents a prototype of vibrotactile wristband using spatiotemporal patterns to help visually impaired users reach an object in the 2D plane in front of them. A pilot study on twelve blindfolded sighted subjects showed that discretizing space in a seven by seven targets matrix and conveying clues with a discrete pattern on the vertical axis and a continuous pattern on the horizontal axis is an intuitive and effective design.

cs.HC↗

arXiv2020

It's All in the Timing: Principles of Transient Distraction Illustrated with Vibrotactile Tasks

Vibration is an efficient way of conveying information from a device to its user, and it is increasingly used for wrist or finger-worn devices such as smart rings. Unexpected vibrations or sounds from the environment may disrupt the perception of such information. Although disruptive effects have been systematically explored in vision and audition, they have been less examined in the haptic domain. Here we briefly review the relevant literature from HCI and psychology, distilling principles of when distraction is likely. We then investigate these principles through four experiments, examining how the timing and modality of relatively rare or unexpected stimuli (surprise distractors) affects the detection and recognition of vibrotactile target patterns. At short distractor-target delays (< 350 ms), both auditory and vibrotactile surprise distractors impaired performance. At a longer delay (1050 ms), performance was not affected overall, even being improved with repeated exposure to the vibrotactile distractors. We discuss the importance of our findings in the context of HCI and cognitive psychology, and we provide design guidelines for mitigating the effects of distraction on haptic devices.

cs.HC↗

arXiv2020

Nudge for Deliberativeness: How Interface Features Influence Online Discourse

Cognitive load is a significant challenge to users for being deliberative. Interface design has been used to mitigate this cognitive state. This paper surveys literature on the anchoring effect, partitioning effect and point-of-choice effect, based on which we propose three interface nudges, namely, the word-count anchor, partitioning text fields, and reply choice prompt. We then conducted a 2*2*2 factorial experiment with 80 participants (10 for each condition), testing how these nudges affect deliberativeness. The results showed a significant positive impact of the word-count anchor. There was also a significant positive impact of the partitioning text fields on the word count of response. The reply choice prompt showed a surprisingly negative affect on the quantity of response, hinting at the possibility that the reply choice prompt induces a fear of evaluation, which could in turn dampen the willingness to reply.

cs.HC↗

arXiv2019

Effects of Moderation and Opinion Heterogeneity on Attitude towards the Online Deliberation Experience

Online deliberation offers a way for citizens to collectively discuss an issue and provide input for policy makers. The overall experience of online deliberation can be affected by multiple factors. We decided to investigate the effects of moderation and opinion heterogeneity on the perceived deliberation experience, by running the first online deliberation experiment in Singapore. Our study took place in three months with three phases. In phase 1, our 2,006 participants answered a survey, that we used to create groups of different opinion heterogeneity. During the second phase, 510 participants discussed about the population issue on the online platform we developed. We gathered data on their online deliberation experience during phase 3. We found out that higher levels of moderation negatively impact the experience of deliberation on perceived procedural fairness, validity claim and policy legitimacy; and that high opinion heterogeneity is important in order to get a fair assessment of the deliberation experience.

cs.HC↗