עברית

Dr. Sarah Ita Levitan

Email
sarah.ita-levitan@biu.ac.il
תחומי מחקר
CV

Ph.D. in Computer Science from Columbia University (2019), supervised by Prof. Julia Hirschberg.

Postdoctoral research at Columbia University.

Assistant Professor at Hunter College, City University of New York (CUNY), before joining Bar-Ilan University.

Research Interests:

  • Speech and Natural Language Processing
  • Computational Paralinguistics
  • Spoken Dialogue and Human Communication
  • Trust, Deception, and Social Perception
  • Machine Learning and Artificial Intelligence
Research

My research focuses on speech and natural language processing, with an emphasis on understanding how people communicate information beyond the words they use. I develop computational methods to analyze acoustic-prosodic and linguistic cues in spoken interactions, exploring how they convey social and psychological information such as trust and deception. My work combines machine learning, speech processing, and natural language processing to better understand human communication and develop socially aware AI systems.

Publications

Selected Publications

[1] Yu, Y., & Levitan, S. I. (2025). Enhancing Trust in Intelligent Virtual Agents: The Role of Acoustic Cues, Lexical Style, and Listener Characteristics in the Perception of Synthesized Speech. ACM International Conference on Intelligent Virtual Agents.

[2] Tyulina, N., Yu, Y., Aloi Emmanouil, T., & Levitan, S. I. (2025). Beyond Face Value: Visual and Auditory Signals in Human and Machine Trust Judgments. ACM Conversational User Interfaces Conference.

[3] Shokri, M., Sharma, V., Filatova, E., Jain, S., & Levitan, S. I. (2024). Subjectivity Detection in English News Using Large Language Models. ACL Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis.

[4] Dey, S., An, G., & Levitan, S. I. (2024). Analysis and Modeling of Self-Reported and Observer-Reported Personality Scores from Text and Speech. Speech Prosody 2024.

[5] Yu, Y., & Levitan, S. I. (2024). What Makes a Conversational Agent Sound Trustworthy? Exploring the Role of Acoustic-Prosodic Factors. Speech Prosody 2024.

[6] Panda, S., & Levitan, S. I. (2022). Deception Detection Within and Across Domains: Understanding and Improving the Performance Gap. ACM Journal of Data and Information Quality.

[7] Nguyen, H., Vente, R. B., Lupea, D., Levitan, S. I., & Hirschberg, J. (2021). Acoustic-Prosodic, Lexical and Demographic Cues to Persuasiveness in Competitive Debate Speeches. Interspeech 2021.

[8] Chen, X., Levitan, S. I., Levine, M., Mandic, M., & Hirschberg, J. (2020). Acoustic-Prosodic and Lexical Cues to Deception and Trust: Deciphering How People Detect Lies. Transactions of the Association for Computational Linguistics, 8, 199–214.

[9] Weise, A., Levitan, S. I., Hirschberg, J., & Levitan, R. (2019). Individual Differences in Acoustic-Prosodic Entrainment in Spoken Dialogue. Speech Communication.

[10] Levitan, S. I., Maredia, A., & Hirschberg, J. (2018). Linguistic Cues to Deception and Perceived Deception in Interview Dialogues. NAACL-HLT 2018.

Full Publication List: Google Scholar

Last Updated Date : 23/10/2026