CHS: Medium: Collaborative Reearch: Bio-behavioral data analytics to enable personalized training of veterans for the future workforce

CHS：中：协作研究：生物行为数据分析，为未来的劳动力提供退伍军人的个性化培训

• 批准号: 1956021
• 负责人: Scott Schaefer
• 金额: $ 30.37万
• 依托单位: Texas A&M Engineering Experiment Station
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1956021&HistoricalAwards=false
• 关键词: CHS; Medium; Collaborative; Reearch; Bio

pThis project promotes fair and ethical treatment of veterans in the future job landscape by providing the empirical knowledge needed to remove implicit bias and misconceptions against veterans and prepare veterans for obtaining and maintaining competitive positions in the future workforce. Despite their strong work ethic and dedication, many veterans in the U.S still face major barriers to participating in the civilian workforce. After separation from duty, service members often participate in a week-long transition assistance program that, at best, can be described as a convenient "one-size-fits-all" solution. Research studying the limitations of the veteran population in entering this dynamically changing job market is scarce and does not provide a full understanding of the challenges faced by the veteran population as well as their train of thought during the time of the job interview. This project gathers empirical evidence to understand veterans' common feelings, thoughts, and potential weaknesses in social effectiveness skills during the civilian job interviews. The project further provides a preliminary assistive technology enabled by artificial intelligence for promoting veterans' interview skills in a tailored and inclusive manner, ultimately preparing them for the future workforce and broadening their participation in fields where they are traditionally underrepresented, such as computing. In addition to interview training, through effective partnerships with industry, this work creates educational materials for promoting unexplored strengths of the veteran population, such as commitment, reliability, and sense of duty, to the potential employers, thereby changing the job hiring culture and providing veterans with more opportunities in the future job landscape./p pThis project explores the above goals through a collaboration between computational and behavioral sciences for acquiring new insights into veterans' experiences during civilian interviews and designing novel technologies for supporting veterans in this task. The research work will be carried out with three technical aims. The first aim is on data collection through focus group discussions and real-life interviews of veterans with industry representatives to identify challenging encounters during the interview. Data include behavioral reactions, physiological reactivity, and subjective assessments of both the interviewer and interviewee, which are examined in association with the interview setting and are further triangulated. The second aim will explore quantifiable measures of interviewees' moment-to-moment stress based on their vocalizations, visual expressions, and physiological reactivity. These quantifiable measures are employed for the preliminary design of training interventions that can assist veterans on coping with stress during the job interview training. The third aim will examine the interviewee's ability to engage with the interviewer. In particular, the researchers will develop new methods in natural language processing and affective computing for detecting overly formal conversational language specific to the military, as well as degradation in social aspects of the interaction from acoustic and visual cues./p pThis award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria./p

P该项目通过提供必要的经验知识，消除对退伍军人的隐性偏见和误解，并为退伍军人在未来劳动力中获得和保持有竞争力的职位做好准备，从而促进在未来的工作环境中公平和合乎道德地对待退伍军人。尽管许多美国退伍军人具有强烈的职业道德和奉献精神，但他们在加入平民劳动力大军方面仍然面临重大障碍。离岗后，服役人员经常参加为期一周的过渡援助计划，充其量可以被描述为方便的“一刀切”的解决方案。研究退伍军人在进入这个动态变化的就业市场方面的局限性的研究很少，也没有提供对退伍军人面临的挑战以及他们在求职面试期间的思路的充分了解。该项目收集了经验证据，以了解退伍军人在文职工作面试中在社会效力技能方面的共同感受、想法和潜在弱点。该项目进一步提供了一种由人工智能支持的初步辅助技术，以量身定制和包容的方式促进退伍军人的面试技能，最终使他们为未来的劳动力做好准备，并扩大他们在传统上代表性不足的领域的参与，如计算机。除了面试培训，通过与业界的有效伙伴关系，这项工作还创建了教育材料，向潜在雇主宣传退伍军人的未开发优势，如承诺、可靠性和责任感，从而改变工作招聘文化，并在未来的工作环境中为退伍军人提供更多机会。/p p本项目通过计算科学和行为科学之间的合作，探索上述目标，以获得对退伍军人在平民面试中的经历的新见解，并设计新技术来支持退伍军人完成这项任务。这项研究工作将以三个技术目标进行。第一个目标是通过焦点小组讨论和对退伍军人与行业代表的真实访谈来收集数据，以确定采访期间遇到的具有挑战性的情况。数据包括面试者和被采访者的行为反应、生理反应和主观评估，这些都是与面试环境相关联的检查，并被进一步三角测量。第二个目标将基于受访者的发声、视觉表达和生理反应来探索受访者时刻压力的可量化测量。这些可量化的措施被用于初步设计培训干预措施，以帮助退伍军人应对求职面试培训期间的压力。第三个目标是考察受访者与面试官互动的能力。特别是，研究人员将在自然语言处理和情感计算方面开发新的方法，以检测特定于军队的过于正式的对话语言，以及根据声音和视觉线索对互动的社交方面的退化。/p p该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。/p

项目成果

“Am I Answering My Job Interview Questions Right?”: A NLP Approach to Predict Degree of Explanation in Job Interview Responses

– 我回答的工作面试问题正确吗？ –：预测工作面试回答中解释程度的 NLP 方法

• DOI: 10.18653/v1/2022.nlp4pi-1.14
• 发表时间: 2022
• 期刊: Empirical Methods in Natural Language Processing (EMNLP
• 作者: Verrap, Raghu;Nirjhar, Ehsanul;Nenkova, Ani;Chaspari, Theodora
• 通讯作者: Chaspari, Theodora

Evaluating Just-In-Time Vibrotactile Feedback for Communication Anxiety

评估沟通焦虑的即时振动触觉反馈

• DOI: 10.1145/3536221.3556590
• 发表时间: 2022
• 期刊: ICMI '22: Proceedings of the 2022 International Conference on Multimodal Interaction
• 作者: Raether, Jason;Nirjhar, Ehsanul Haque;Chaspari, Theodora
• 通讯作者: Chaspari, Theodora

Investigating the Interplay Between Self-Reported and Bio-Behavioral Measures of Stress: A Pilot Study of Civilian Job Interviews with Military Veterans

调查压力自我报告与生物行为测量之间的相互作用：对退伍军人进行平民工作面试的试点研究

• DOI: 10.1109/acii55700.2022.9953815
• 发表时间: 2022
• 期刊: 2022 10th International Conference on Affective Computing and Intelligent Interaction (ACII
• 作者: Haque Nirjhar, Ehsanul;Sakib, Md Nazmus;Hagen, Ellen;Rani, Neha;Lynn Chu, Sharon;Arthur, Winfred;Behzadan, Amir H.;Chaspari, Theodora
• 通讯作者: Chaspari, Theodora

Knowledge- and Data-Driven Models of Multimodal Trajectories of Public Speaking Anxiety in Real and Virtual Settings

真实和虚拟环境中公共演讲焦虑多模态轨迹的知识和数据驱动模型

• DOI: 10.1145/3462244.3479964
• 发表时间: 2021
• 期刊: 23rd ACM International Conference on Multimodal Interaction (ICMI 2021
• 作者: Nirjhar, Ehsanul Haque;Behzadan, Amir H.;Chaspari, Theodora
• 通讯作者: Chaspari, Theodora