Computing and Information Systems - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 924
-
ItemSame graph, different data: A usability study of a student-facing dashboard based on self-regulated learning theory(Australasian Society for Computers in Learning in Tertiary Education (ASCILITE), 2022)Student-facing learning analytics dashboards have the potential to reconnect students with their purpose for learning, reminding them of their goals and promoting reflection about their learning journey. However, far less is known about the specifics of the relationship between different types of visualisations and data presented in dashboards and their impact on students’ motivation. In this study, we used a Human-Centred Design method across three iterations to (1) understand how students prioritise similar visualisations when presenting different data (2) examine how they interact with these, and (3) propose a dashboard design that would accommodate students’ different motivational needs. In the first iteration, 26 participants ranked their preferred visualisations using paper prototypes; in the second iteration, a digital wireframe was created based on the results from the first iteration to conduct user tests with two participants; and in the third iteration, a high-fidelity prototype was created to reflect findings from the previous iterations. Overall, findings showed that students mostly valued setting goals and monitoring their progress from a multiple goals approach, and were reluctant about comparing their performance with peers due to concerns related to promoting unproductive competition amongst peers and data privacy. Implications for educators and learning designers are discussed.
-
ItemThe Impact of Cognitive Load on Students’ Academic Writing: An Authorship Verification Investigation(Australasian Society for Computers in Learning in Tertiary Education (ASCILITE), 2022)Automatic authorship verification is known to be a challenging machine learning task. In this paper, we examine the efficacy of an enhanced common n-gram profile-based approach to assist educational institutions to validate students' essays and assignments through their writing styles. We investigated the impact that essays with different cognitive load requirements have in students' writing styles, which may or may not impact authorship verification methods. A total of 46 undergraduate students completed six essays in a laboratory study. Although results showed small and mixed effects of the tasks differing in cognitive load on the different writing product metrics, students' essays and assignments texts contained features that remained stable across essays requiring different levels of cognitive load. These results suggest that our approach could be successfully used in authorship verification, potentially helping to address issues related to academic integrity in higher education settings.
-
ItemStatistical Modelling for Simulating and Interpreting an Egg Packaging Process for Giveaway Mitigation(AIS, 2022)Giveaway, the excess product being packed into orders, contributes to revenue loss that pre-packaged food manufacturers care about the most. In collaboration with an egg packaging company, this study aims to discover operation rules to mitigate the giveaway in egg orders. For that, two variables have been raised as potential controllable factors of the giveaway. One statistical model has been developed to better interpret the experimental results by understanding the underlying rules of the egg grading machine. The experiments have been accurately reproduced by a simulation using the estimated model parameters, indicating the model's success. Based on the experiment results, we claim that the number of accepted egg grades significantly influences the final giveaway ratio. Limitations and further potentials of the statistical model have also been discussed.
-
ItemSurvival text regression for time-to-event prediction in conversations(Association for Computational Linguistics, 2021)Time-to-event prediction tasks are common in conversation modelling, for applications such as predicting the length of a conversation or when a user will stop contributing to a platform. Despite the fact that it is natural to frame such predictions as regression tasks, recent work has modelled them as classification tasks, determining whether the time-to-event is greater than a pre-determined cut-off point. While this allows for the application of classification models which are well studied in NLP, it imposes a formulation that is contrived, as well as less informative. In this paper, we explore how to handle time-to-event forecasting in conversations as regression tasks. We focus on a family of regression techniques known as survival regression, which are commonly used in the context of healthcare and reliability engineering. We adapt these models to time-to-event prediction in conversations, using linguistic markers as features. On three datasets, we demonstrate that they outperform commonly considered text regression methods and comparable classification models.
-
ItemLeveraging Wikipedia article evolution for promotional tone detection(Association for Computational Linguistics, 2022)Detecting biased language is useful for a variety of applications, such as identifying hyperpartisan news sources or flagging one-sided rhetoric. In this work we introduce WikiEvolve, a dataset for document-level promotional tone detection in English. Unlike previously proposed datasets, it contains seven versions of the same article from Wikipedia, from different points in its revision history; one with promotional tone, and six without it. We adapt the gradient reversal layer framework to encode two article versions simultaneously, and thus leverage the training signal present in the multiple versions. In our experiments, our proposed adaptation of gradient reversal improves the accuracy of four different architectures on both in-domain and out of- domain evaluation.
-
ItemI Beg to Differ: A study of constructive disagreement in online conversations(Association for Computational Linguistics, 2021)Disagreements are pervasive in human communication. In this paper we investigate what makes disagreement constructive. To this end, we construct WikiDisputes, a corpus of 7 425 Wikipedia Talk page conversations that contain content disputes, and define the task of predicting whether disagreements will be escalated to mediation by a moderator. We evaluate feature-based models with linguistic markers from previous work, and demonstrate that their performance is improved by using features that capture changes in linguistic markers throughout the conversations, as opposed to averaged values. We develop a variety of neural models and show that taking into account the structure of the conversation improves predictive accuracy, exceeding that of feature-based models. We assess our best neural model in terms of both predictive accuracy and uncertainty by evaluating its behaviour when it is only exposed to the beginning of the conversation, finding that model accuracy improves and uncertainty reduces as models are exposed to more information.
-
ItemNo Preview AvailableImmediate-Access Indexing Using Space-Efficient Extensible Arrays(ACM, 2022-12-15)
-
ItemNo Preview Available
-
ItemNo Preview AvailableOlder Adults Using Technology for Meaningful Activities During COVID-19: An Analysis Through the Lens of Self-Determination Theory(ACM, 2023-04-19)Restrictions during the COVID-19 pandemic significantly affected people’s opportunities to engage in activities that are meaningful to their lives. In response to these constraints, many people, including older adults, turned to digital technologies as alternative ways to pursue meaningful activities. These technology-mediated activities, however, presented new challenges for older adults’ everyday use of technology. In this paper, we investigate how older adults used digital technologies for meaningful activities during COVID-19 restrictions. We conducted in-depth interviews with 40 older adults and analyzed the interview data through the lens of self-determination theory (SDT). Our analysis shows that using digital technologies for meaningful activities can both support and undermine older people’s three basic psychological needs for autonomy, competence, and relatedness. We argue that future technologies should be designed to empower older adults’ content creation, engagement in personal interests, exploration of technology, effortful communication, and participation in beneficent activities.
-
ItemNo Preview Available