检索结果-内蒙古大学图书馆

Exploring Trade-Offs for Online Mental Health Matching: Agent-Based Modeling Study

JMIR Formative Research 2024年 8卷 e58241页

作者： Liu, Yuhan Fang, Anna Moriarty, Glen Firman, Cristopher Kraut, Robert E. Zhu, Haiyi Department of Computer Science Princeton University Princeton NJ United States Human-Computer Interaction Institute Carnegie Mellon University Pittsburgh PA United States 7 Cups Wilmington DE United States

Background: Online mental health communities (OMHCs) are an effective and accessible channel to give and receive social support for individuals with mental and emotional issues. However, a key challenge on these platforms is finding suitable partners to interact with given that mechanisms to match users are currently underdeveloped or highly naive. Objective: In this study, we collaborated with one of the world’s largest OMHCs;our contribution is to show the application of agent-based modeling for the design of online community matching algorithms. We developed an agent-based simulation framework and showcased how it can uncover trade-offs in different matching algorithms between people seeking support and volunteer counselors. Methods: We used a comprehensive data set spanning January 2020 to April 2022 to create a simulation framework based on agent-based modeling that replicates the current matching mechanisms of our research site. After validating the accuracy of this simulated replication, we used this simulation framework as a “sandbox” to test different matching algorithms based on the deferred acceptance algorithm. We compared trade-offs among these different matching algorithms based on various metrics of interest, such as chat ratings and matching success rates. Results: Our study suggests that various tensions emerge through different algorithmic choices for these communities. For example, our simulation uncovered that increased waiting time for support seekers was an inherent consequence on these sites when intelligent matching was used to find more suitable matches. Our simulation also verified some intuitive effects, such as that the greatest number of support seeker–counselor matches occurred using a “first come, first served” protocol, whereas relatively fewer matches occurred using a “last come, first served” protocol. We also discuss practical findings regarding matching for vulnerable versus overall populations. Results by demographic group reveal

关键词： agent-based modeling algorithmic matching mental health online communities social computing

来源：评论

学校读者我要写书评

暂无评论

Cruising Queer HCI on the DL: A Literature Review of LGBTQ+ People in HCI 24

Cruising Queer HCI on the DL: A Literature Review of LGBTQ+ ...

引用

Proceedings of the CHI Conference on human Factors in Computing Systems

作者： Jordan Taylor Ellen Simpson Anh-Ton Tran Jed R. Brubaker Sarah E Fox Haiyi Zhu Human-Computer Interaction Institute Carnegie Mellon University United States Department of Information Science University of Colorado United States Georgia Institute of Technology United States Department of Information Science University of Colorado Boulder United States

ISBN: (纸本)9798400703300

LGBTQ+ people have received increased attention in HCI research, paralleling a greater emphasis on social justice in recent years. However, there has not been a systematic review of how LGBTQ+ people are researched or discussed in HCI. In this work, we review all research mentioning LGBTQ+ people across the HCI venues of CHI, CSCW, DIS, and TOCHI. Since 2014, we find a linear growth in the number of papers substantially about LGBTQ+ people and an exponential increase in the number of mentions. Research about LGBTQ+ people tends to center experiences of being politicized, outside the norm, stigmatized, or highly vulnerable. LGBTQ+ people are typically mentioned as a marginalized group or an area of future research. We identify gaps and opportunities for (1) research about and (2) the discussion of LGBTQ+ in HCI and provide a dataset to facilitate future Queer HCI research.

关键词： LGBTQ+ people Literature Review Marginalized Communities Queer HCI Queer People

来源：评论

学校读者我要写书评

暂无评论

Investigating the Role of Metaphors in human-AI Conversation and Engagement

Investigating the Role of Metaphors in Human-AI Conversation...

引用

IEEE International Conference on Data Mining Workshops (ICDM Workshops)

作者： Pragati Maheshwary Qiawen Liu Rui Mao Human-Computer Interaction Institute Carnegie Mellon University United States Department of Psychology University of Wisconsin-Madison United States College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (数字)9798331530631

ISBN: (纸本)9798331530648

Metaphorical expressions are widely used in daily communication between humans to improve the understanding of both complex and abstract concepts. However, it is unclear whether the usage of metaphorical language is helpful for enhancing the conversational engagement between humans and AI. In this work, we leverage a state-of-the-art computational metaphor processing tool to gain insights from human and ChatGPT conversations. Our quantitative analysis finds that although metaphors may enhance the quality of human-AI interactions, they do not directly lead to higher levels of conversational engagement, which is measured by the duration of the conversation. However, regression analysis shows a notable relationship between user and ChatGPT metaphor usage, suggesting that ChatGPT is adept at reflecting the linguistic style of users, especially in terms of metaphorical language. Additional topic modeling and concept mapping analyses further explored the patterns of metaphorical language across various engagement levels and topics in user and ChatGPT messages.

关键词： Analytical models Conferences Oral communication Linguistics Chatbots Regression analysis Data mining Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Private Synthetic Text Generation with Diffusion Models

arXiv

引用

arXiv 2024年

作者： Ochs, Sebastian Habernal, Ivan Trustworthy Human Language Technologies 1 Department of Computer Science Technical University of Darmstadt Germany Research Center Trustworthy Data Science and Security of the University Alliance Ruhr Faculty of Computer Science Ruhr University Bochum Germany

How capable are diffusion models of generating synthetics texts? Recent research shows their strengths, with performance reaching that of auto-regressive LLMs. But are they also good in generating synthetic data if the training was under differential privacy? Here the evidence is missing, yet the promises from private image generation look strong. In this paper we address this open question by extensive experiments. At the same time, we critically assess (and reimplement) previous works on synthetic private text generation with LLMs and reveal some unmet assumptions that might have led to violating the differential privacy guarantees. Our results partly contradict previous non-private findings and show that fully open-source LLMs outperform diffusion models in the privacy regime. Our complete source codes, datasets, and experimental setup are publicly available to foster future research1 © 2024, CC BY-SA.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Designing a Sustainable Material for 3D Printing with Spent Coffee Grounds 23

Designing a Sustainable Material for 3D Printing with Spent ...

引用

Proceedings of the 2023 ACM Designing Interactive Systems Conference

作者： Michael L. Rivera S. Sandra Bae Scott E. Hudson ATLAS Institute and Department of Computer Science University of Colorado Boulder United States ATLAS Institute University of Colorado Boulder United States Human-Computer Interaction Institute Carnegie Mellon University United States

ISBN: (纸本)9781450398930

The widespread adoption of 3D printers exacerbates existing environmental challenges as these machines increase energy consumption, waste output, and the use of plastics. Material choice for 3D printing is tightly connected to these challenges, and as such researchers and designers are exploring sustainable alternatives. Building on these efforts, this work explores using spent coffee grounds as a sustainable material for prototyping with 3D printing. This material, in addition to being compostable and recyclable, can be easily made and printed at home. We describe the material in detail, including the process of making it from readily available ingredients, its material characteristics and its printing parameters. We then explore how it can support sustainable prototyping practices as well as HCI applications. In reflecting on our design process, we discuss challenges and opportunities for the HCI community to support sustainable prototyping and personal fabrication. We conclude with a set of design considerations for others to weigh when exploring sustainable materials for 3D printing and prototyping.

关键词： environmental sustainability zero-waste prototyping personal fabrication 3D printing bio-based materials

来源：评论

学校读者我要写书评

暂无评论

When Does an Individual Accept Misinformation? An Extended Investigation Through Cognitive Modeling

引用

Computational Brain and Behavior 2022年第2期5卷 244-260页

作者： Borukhson, David Lorenz-Spreen, Philipp Ragni, Marco Department for Computer Science University of Freiburg Freiburg Germany Center for Adaptive Rationality Max Planck Institute for Human Development Berlin Germany Predictive Analytics Technical University Chemnitz Chemnitz Germany

A new phenomenon is the spread and acceptance of misinformation and disinformation on an individual user level, facilitated by social media such as Twitter. So far, state-of-the-art socio-psychological theories and cognitive models focus on explaining how the accuracy of fake news is judged on average, with little consideration of the individual. In this paper, a breadth of core models are comparatively assessed on their predictive accuracy for the individual decision maker, i.e., how well can models predict an individual’s decision before the decision is made. To conduct this analysis, it requires the raw responses of each individual and the implementation and adaption of theories to predict the individual’s response. Building on methods formerly applied on smaller and more limited datasets, we used three previously collected large datasets with a total of 3794 participants and searched for, analyzed and refined existing classical and heuristic modeling approaches. The results suggest that classical reasoning, sentiment analysis models and heuristic approaches can best predict the “Accept” or “Reject” response of a person, headed by a model put together from research by Jay Van Bavel, while other models such as an implementation of “motivated reasoning” performed worse. Further, hybrid models that combine pairs of individual models achieve a significant increase in performance, pointing to an adaptive toolbox. © 2022, The Author(s).

关键词： Fake news detection Hybrid cognitive models Predictive modeling Socio-psychological theories

来源：评论

学校读者我要写书评

暂无评论

Ball sition ature bedded Group Activity Recognition del for Team Sport Games 4

Ball sition ature bedded Group Activity Recognition del for ...

引用

4th International Conference on Machine Learning and Intelligent Systems, MLIS 2022

作者： Jamsrandorj, Ankhzaya Chao, Vanyi Oo, Yin May Mun, Kyung-Ryoul Kim, Jinwook Department of Human Computer Interface & Robotics Engineering University of Science & Technology Korea Republic of Department of Ai Robotics University of Science & Technology Korea Republic of Center for Artificial Intelligence Korea Institute of Science and Technology Korea Republic of

ISBN: (纸本)9781643683560

Most group activity recognition models focus mainly on spatio-temporal features from the players in sports games. Often they do not pay enough attention to the game object, which heavily affects not only individual action but also a group activity. We propose a new group activity recognition model for sports games that incorporates players' motion information and game object positional information. The proposed method uses a transformer encoder for temporal feature extraction and a 'simple' conventional convolutional neural network for extracting spatial features and fusing them with the relative ball position-embedded features. The experimental results show that our model achieved comparable results to state-of-the-art methods on the Volleyball dataset by using only one transformer encoder block and the ball position. © 2022 The authors and IOS Press.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

The Mobile Office: A Mobile AR Systems for Productivity Applications in Industrial Environments 13th

The Mobile Office: A Mobile AR Systems for Productivity Appl...

引用

13th International Conference on Virtual, Augmented and Mixed Reality, VAMR 2021, Held as Part of the 23rd HCI International Conference, HCII 2021

作者： Linares Garcia, Daniel Antonio Dongre, Poorvesh Roofigari-Esfahan, Nazila Bowman, Doug A. Department of Building Construction Virginia Tech BlacksburgVA24060 United States Department of Computer Science Virginia Tech BlacksburgVA24060 United States Center for Human-Computer Interaction Virginia Tech BlacksburgVA24060 United States

ISBN: (纸本)9783030775988

This article proposes the Mobile Office, an AR-Based System for productivity applications in industrial environments. It focuses on addressing workers’ needs while mobilizing in complex environments and when workers want to do productive work similar to a workstation setting. For this purpose, the Mobile Office relies on a bi-modal approach (mobile and static modes) to addresses both scenarios while considering critical aspects such as UI, ergonomics, interaction, safety, and cognitive user abilities. Its development relies first on a systematic literature review for establishing guidelines and system aspects. Then AR-UI mockups are presented to incorporate literature and authors’ expertise in this area. Three hardware configurations are also presented for the implementation of the Mobile Office. Validation of the Mobile Office was made through a survey to potential users that provided their feedback about their perceptions of proposed system. The survey results revealed concordance of critical aspects of particular importance for effective productivity support on the Mobile Office’s focus scenarios. We incorporated these critical aspects and suggested future research direction for the Mobile Office’s further development and significance. © 2021, Springer Nature Switzerland AG.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Automatic detection and classification algorithm of thyroid nodules in CT images based on YOLOv5s 9

Automatic detection and classification algorithm of thyroid ...

引用

9th International Conference on computer and Communications, ICCC 2023

作者： Guo, Ruifeng Xu, Lei Guo, Jiahui Wang, Hongliang Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Shenyang China Liaoning Prov. Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China The First Hospital of China Medical University Department of Endocrinology and Metabolism Shenyang China

ISBN: (纸本)9798350317251

Thyroid nodular lesions are one of the most common diseases in the population. As the number of patients increases, it is clinically important to provide physicians with an accurate early aid to determine the benignity and malignancy of thyroid nodules in order to avoid unnecessary surgery and reduce patient burden. In this paper, we propose an improved Yolov5s-based target detection algorithm for benign and malignant thyroid nodules for thyroid nodule classification and identification. Replacing the backbone network of Yolov5s with ResNet18 to reduce the complexity of the model and the number of parameters;introducing the CBAM attention mechanism into the Yolov5s algorithm to improve the ability to extract features;Modify the spatial pyramid pooling module SPP to SimSPPF to improve the training speed of the algorithm;replace GIoU Loss with CIoU-Focal Loss as the loss function of the algorithm to improve the localization accuracy while increasing the regression rate of the bounding box. The experimental results show that the improved Yolov5s achieved an average accuracy of 92.9%, which is 2.9 percentage points higher than the average accuracy of the original algorithm, and can effectively improve the accuracy and efficiency of nodule detection. © 2023 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Sequence-based Segmentation and Non-Temporal Visualizations for Pilot Performance Assessment

Sequence-based Segmentation and Non-Temporal Visualizations ...

引用

AIAA science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Sheets, David A. Amiruzzaman, Md Blake Stringer, D. Strzempkowski, Brian Zhao, Ye Department of Computer Science Kent State University 800 E Summit St KentOH44242 United States Department of Computer Science West Chester University 25 University Avenue # 150 West ChesterPA19383 United States Center for Aviation Studies Department of Mechanical & Aerospace Engineering The Ohio State University 228B Bolz Hall 2036 Neil Avenue ColumbusOH43210 United States Center for Aviation Studies College of Engineering College of Education & Human Ecology The Ohio State University 228 Bolz Hall ColumbusOH43210 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

Pilot shortages are predicted to increase over the next decades, resulting in a need to increase the number of qualified pilots. A challenge in meeting this need is maintaining the quality of the training while increasing the throughput. Data-driven approaches, supported by visual analytics techniques, offer a means to meet this challenge and possibly reduce training time and/or improve quality. In this study, we examine the Airman Certification Standards (ACS) and Federal Aviation Administration (FAA) performance maneuvers relevant to initial pilot training. Decomposition methods are applied to the maneuver to establish analyzable components and remove time-related variability. This representation supports a general comparability of maneuver instances, allowing quantification of pilot improvements as well as more direct comparability to gold standards. The decomposition also increases relevance for instructional feedback against individual segments reflecting pilot considerations during the maneuver. Visualizations are applied to further facilitate student-instructor discussion and actionable student feedback. A volume of actual training data is analyzed and explored through user evaluation with aviation experts and students to validate technique applicability. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：