no code implementations • SEMEVAL 2017 • Angel Maredia, Kara Schechtman, Sarah Ita Levitan, Julia Hirschberg
Collecting spontaneous speech corpora that are open-ended, yet topically constrained, is increasingly popular for research in spoken dialogue systems and speaker state, inter alia.
no code implementations • NAACL 2018 • Sarah Ita Levitan, Angel Maredia, Julia Hirschberg
We explore deception detection in interview dialogues.
no code implementations • WS 2019 • Jonathan Zomick, Sarah Ita Levitan, Mark Serper
In this paper we leverage the vast amount of data available from social media and use statistical and machine learning approaches to study linguistic characteristics of SZ.
no code implementations • TACL 2020 • Xi (Leslie) Chen, Sarah Ita Levitan, Michelle Levine, M, Marko ic, Julia Hirschberg
We analyzed the acoustic-prosodic and linguistic characteristics of language trusted and mistrusted by raters and compared these to characteristics of actual truthful and deceptive language to understand how perception aligns with reality.
1 code implementation • NAACL (NLP4IF) 2021 • Subhadarshi Panda, Sarah Ita Levitan
We present machine learning classifiers to automatically identify COVID-19 misinformation on social media in three languages: English, Bulgarian, and Arabic.
no code implementations • EMNLP (Louhi) 2020 • Zhengping Jiang, Sarah Ita Levitan, Jonathan Zomick, Julia Hirschberg
We address the problem of automatic detection of psychiatric disorders from the linguistic content of social media posts.
no code implementations • ACL 2022 • Subhadarshi Panda, Sarah Ita Levitan
With the increase of deception and misinformation especially in social media, it has become crucial to be able to develop machine learning methods to automatically identify deceptive language.
1 code implementation • EMNLP (ALW) 2020 • Ishaan Arora, Julia Guo, Sarah Ita Levitan, Susan McGregor, Julia Hirschberg
Most efforts at identifying abusive speech online rely on public corpora that have been scraped from websites using keyword-based queries or released by site or platform owners for research purposes.
no code implementations • GermEval 2021 • Subhadarshi Panda, Sarah Ita Levitan
In this paper we investigate the efficacy of using contextual embeddings from multilingual BERT and German BERT in identifying fact-claiming comments in German on social media.
no code implementations • NAACL (CLPsych) 2021 • Zhengping Jiang, Jonathan Zomick, Sarah Ita Levitan, Mark Serper, Julia Hirschberg
We address the problem of predicting psychiatric hospitalizations using linguistic features drawn from social media posts.