An Agent for Competing with Humans in a Deceptive Game Based on Vocal Cues

Mansbach, Noa; Neiterman, Evgeny Hershkovitch; Azaria, Amos

doi:10.21437/interspeech.2021-83

Cited by 3 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Textual lie detection focuses on lexical cues that are prevalent in intentional lies (Masip et al, 2012) and examines the author's intentionit identifies whether the writer is intentionally distorting actual information. If the authors decide to distort the information, the lie detector is expected to identify such intention (Mansbach et al, 2021;Barsever et al, 2020). We use a BERT-based lie classifier to assign the threads into a true or false category.…”

Section: Overall Structurementioning

confidence: 99%

Proceedings of the Tenth International Workshop on Natural Language Processing for Social Media

2022

View full text Add to dashboard Cite

Happy 10th Anniversary to SocialNLP!It is our great pleasure to welcome you to the Tenth Workshop on Natural Language Processing for Social Media-SocialNLP 2022, associated with NAACL 2022. SocialNLP is an inter-disciplinary area of natural language processing (NLP) and social computing. We hold SocialNLP twice a year: one in the NLP venue, the other in the associated venue such as those for web technology or artificial intelligence. This year the other version has been successfully held in conjunction with TheWebConf 2022 (formerly WWW), and we are very happily looking forward to the NLP version in NAACL 2022. We are very glad that the number of submissions to this year's workshop keeps increasing, and the submissions themselves were still of high quality with the accepted threshold of 3.33 (maximum 5), which again leads to a competitive selection process. We received submissions from Asia, Europe, and the United States. Considering the review process is rigorous and we want to encourage authors to participate in the workshop, we accepted 8 oral papers. These exciting papers include novel and practical topics for researchers working on NLP for social media, such as bias mitigation, domain transfer, and dataset constructed for the newly emerged research problems. We believe they will benefit our research community.On this 10th anniversary, we would like to share our happiness and celebrate the success together with our community members with the special speaker reunion event. Most of our previous invited speakers, including Prof.

show abstract

Section: Overall Structurementioning

confidence: 99%

Proceedings of the Tenth International Workshop on Natural Language Processing for Social Media

2022

View full text Add to dashboard Cite

show abstract

Detecting Rumor Veracity with Only Textual Information by Double-Channel Structure

Kim¹,

Yoon²

2022

Proceedings of the Tenth International Workshop on Natural Language Processing for Social Media

View full text Add to dashboard Cite

Kyle (1985) proposes two types of rumors: informed rumors that are based on some private information and uninformed rumors that are not based on any information (i.e. bluffing). Also, prior studies find that when people have credible source of information, they are likely to use a more confident textual tone in their spreading of rumors. Motivated by these theoretical findings, we propose a double-channel structure to determine the ex-ante veracity of rumors on social media. Our ultimate goal is to classify each rumor into true, false, or unverifiable category. We first assign each text into either certain (informed rumor) or uncertain (uninformed rumor) category. Then, we apply lie detection algorithm to informed rumors and thread-reply agreement detection algorithm to uninformed rumors. Using the dataset of Se-mEval 2019 Task 7, which requires ex-ante threefold classification (true, false, or unverifiable) of social media rumors, our model yields a macro-F1 score of 0.4027, outperforming all the baseline models and the second-place winner (Gorrell et al., 2019). Furthermore, we empirically validate that the double-channel structure outperforms single-channel structures which use either lie detection or agreement detection algorithm to all posts. 1

show abstract

Meta Learning Based Deception Detection from Speech

Mansbach

Azaria

2023

Applied Sciences

View full text Add to dashboard Cite

It is difficult to overestimate the importance of detecting human deception, specifically by using speech cues. Indeed, several works attempt to detect deception from speech. Unfortunately, most works use the same people and environments in training and in testing. That is, they do not separate training samples from test samples according to the people who said each statement or by the environments in which each sample was recorded. This may result in less reliable detection results. In this paper, we take a meta-learning approach in which a model is trained on a variety of learning tasks to enable it to solve new learning tasks using only a few samples. In our approach, we split the data according to the persons (and recording environment), i.e., some people are used for training, and others are used for testing only, but we do assume a few labeled samples for each person in the data set. We introduce CHAML, a novel deep learning architecture that receives as input the sample in question along with two more truthful samples and non-truthful samples from the same person. We show that our method outperforms other state-of-the-art methods of deception detection based on speech and other approaches for meta-learning on our data-set. Namely, CHAML reaches an accuracy of 61.34% and an F1-Score of 0.3857, compared to an accuracy of only 55.82% and an F1-score of only 0.3444, achieved by a previous, most recent approach.

show abstract

An Agent for Competing with Humans in a Deceptive Game Based on Vocal Cues

Cited by 3 publications

References 16 publications

Proceedings of the Tenth International Workshop on Natural Language Processing for Social Media

Proceedings of the Tenth International Workshop on Natural Language Processing for Social Media

Detecting Rumor Veracity with Only Textual Information by Double-Channel Structure

Meta Learning Based Deception Detection from Speech

Contact Info

Product

Resources

About