Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 6 of 6
Full-Text Articles in Cognitive Science
Cognitive Feedback Theories And Artificial Intelligence: A Case For A Grammarly Of Ui/Ux Design, Jordan Buchanan Paff
Cognitive Feedback Theories And Artificial Intelligence: A Case For A Grammarly Of Ui/Ux Design, Jordan Buchanan Paff
Dartmouth College Undergraduate Theses
This thesis is concerned with utilizing artificial intelligence and machine learning (AI/ML) techniques and cognitive theories of feedback to enhance learning outcomes in the field of user interface and user experience (UI/UX) design. The capabilities of AI/ML have expanded immensely over the past several years, and it is now being effectively used in software programs like Grammarly, a tool that provides intelligent feedback on writing skills including grammar, tone, and clarity. Grammarly has been uniquely successful as a feedback tool because it relies on lessons from cognitive science regarding student feedback and learning outcomes. Currently, there is no comparable software …
Possibility Is Not A Luxury: The Role Of Identity In Representations Of Possibility, Hannah M. Lebaron
Possibility Is Not A Luxury: The Role Of Identity In Representations Of Possibility, Hannah M. Lebaron
Dartmouth College Undergraduate Theses
In what ways are our expectations of others and their behaviors limited by the ways they are identified? Broadly, this project asks how identity traits are considered across judgments about which social roles people can assume. This work is an interdisciplinary project that exists within the fields of both Cognitive Science and Women’s, Gender, and Sexuality Studies. As such, the first chapter explores the central issues of identity conception from the perspective of feminist theory, including a discussion of category destabilization, intersectionality, and knowledge production in the context of feminist science studies. 4 empirical studies were launched with methods informed …
Probing Nlp Conceptual Relatedness Judgments Through The Word-Based Board Game Codenames, Tracey Mills
Probing Nlp Conceptual Relatedness Judgments Through The Word-Based Board Game Codenames, Tracey Mills
Dartmouth College Undergraduate Theses
In this paper I evaluate the ability of different Natural Language Processing (NLP)
techniques to make human-like word relatedness judgements in a variant of the word-based board game Codenames. I analyze a variety of statistical and knowledge based approaches, combinations of these, and techniques for incorporating the wider game context into relatedness judgements. While no approach explored here reaches human performance, simple word embedding based approaches incorporate a surprising amount of the useful information captured by other techniques. I attempt to characterize the limitations of these approaches in relation to human game play, although differences are largely not systematic. Finally, …
Metaphors Matter: Top-Down Effects On Anthropomorphism, Hailey Austine Scherer
Metaphors Matter: Top-Down Effects On Anthropomorphism, Hailey Austine Scherer
Dartmouth College Undergraduate Theses
Anthropomorphism, or the attribution of human mental states and characteristics to non-human entities, has been widely demonstrated to be cued automatically by certain bottom-up appearance and behavioral features in machines. In this thesis, I argue that the potential for top-down effects to influence anthropomorphism has so far been underexplored. I motivate and then report the results of a new empirical study suggesting that top-down linguistic cues, including anthropomorphic metaphors, personal pronouns, and other grammatical constructions, increase anthropomorphism of a robot. As robots and other machines become more integrated into human society and our daily lives, more thorough understanding of the …
Why Do We Follow Rules? An Exploration Of Normativity And Possibility, Eliza Jane Shaeffer
Why Do We Follow Rules? An Exploration Of Normativity And Possibility, Eliza Jane Shaeffer
Dartmouth College Undergraduate Theses
The way we interact with the world is governed by a body of rules, many of which are unspoken. What makes these rules so compelling? How do they interact with our decision-making infrastructure? In a series of three studies, this article explores the shared adaptive sampling model’s ability to account for normative behaviors, using a time pressure paradigm in which subjects (N = 399) recruited via Amazon Mechanical Turk quickly judged whether actions of various degrees of moral permissibility and social acceptability were possible or impossible in a certain context (Phillips & Cushman, 2017; Phillips, Morris, & Cushman, 2019). When …
A Deep Learning Approach To Understanding Real-World Scene Perception In Autism, Erica Lindsey Busch
A Deep Learning Approach To Understanding Real-World Scene Perception In Autism, Erica Lindsey Busch
Dartmouth College Undergraduate Theses
Autism is a multifaceted neurodevelopmental condition. Around 90% of individuals with autism experience sensory sensitivities, particularly impacting visual perception. Despite this high percentage, previous studies investigating visual perception in autism impose severe limitations on our understanding. In many of these experiments, their stimuli and experimental methods are un-naturalistic and produce unreproducible and conflicting results. In this study, we investigate the nature of the real-world visual experience in autism with a cutting-edge experimental approach. First, we use virtual reality headsets with eye-trackers to measure gaze behavior while individuals freely explore real-world, everyday scenes. Then, we compare their gaze behavior to the …