Inducing rapport-building behaviors in interaction with an embodied conversational agent

Novick, David G.; Afravi, Mahdokht; Camacho, Adriana; Hinojos, Laura J.; Rodriguez, Aaron E.

doi:10.1145/3267851.3267889

Cited by 3 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…chatbots). While not directly related to spambot detection, such work has attempted to produce agents with empathy (Rashkin et al, 2019), trust (Novick et al, 2018) and emotion (Zhou and Wang, 2018;Huber et al, 2018) as well as general personalizations (Li et al, 2016;Zhang et al, 2018;Mazaré et al, 2018). As researchers build machines imbued with more sophisticated human attributes, we can expect similar machines to be used for spamming purposes.…”

Section: Related Workmentioning

confidence: 99%

Characterizing Social Spambots by their Human Traits

Giorgi¹,

Ungar²,

Schwartz³

2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

Social spambots, an emerging class of spammers attempting to emulate people, are difficult for both human annotators and classic bot detection techniques to reliably distinguish from genuine accounts. We examine this human emulation through studying the human characteristics (personality, gender, age, emotions) exhibited by social spambots' language, hypothesizing the values for these attributes will be unhuman-like (e.g. unusually high or low). We found our hypothesis mostly disconfirmed -individually, social bots exhibit very human-like attributes. However, a striking pattern emerged when consider the full distributions of these estimated human attributes: social bots were extremely similar and average in their expressed personality, demographics, and emotion (in contrast with traditional bots which we found to exhibit more variance and extreme values than genuine accounts). We thus consider how well social bots can be identified only using the 17 variables of these human attributes and ended up with a new state of the art in social spambot detection (e.g. F 1 = .946). Further, simulating the situation of not knowing the bots a priori, we found that even an unsupervised clustering using the same 17 attributes could yield nearly as accurate of social bot identification (F 1 = 0.925).

show abstract