Implicit Perception of Differences between NLP‐Produced and Human‐Produced Language in the Mentalizing Network

Wei, Zhengde; Chen, Ying; Zhao, Qian; Zhang, Pengyu; Zhou, Longxi; Ren, Jiecheng; Piao, Yi; Qiu, Bensheng; Xie, Xing; Wang, Suiping; Liu, Jia; Zhang, Daren; Kadosh, Roi Cohen; Zhang, Xiaochu

doi:10.1002/advs.202203990

Cited by 4 publications

(3 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Recent Advances in Multi‐Scale Piezoresistive Interfaces for MXene‐Based Flexible Sensors

Ge,

Sun,

Huang

et al. 2024

Adv Materials Technologies

View full text Add to dashboard Cite

Flexible piezoresistive sensors hold great promise in biomedicine and personal motion detection, attracting significant attention from researchers. Particularly, two‐dimensional (2D) MXene has made remarkable strides in biomedicine, electromagnetic shielding, and other practical applications, due to its exceptional hydrophilicity, biocompatibility, mechanical properties, surface functional groups, and large specific surface area. The ease of composite material formation further makes it ideal for high‐sensitivity flexible sensors. This paper summarizes the principal structural configurations for the multi‐scale interfaces, performance assessment metrics, and the corresponding sensing mechanisms of flexible piezoresistive sensors. Subsequently, the main characteristics and synthesis methods of MXene, especially the related applications and parameters are introduced in detail. The research trends and typical applications of MXene‐based flexible piezoresistive sensors focused on film structures, fiber structures, 3D structures, and hydrogel structures, are highlighted systematically. In addition, the challenges and prospects that promoting the advancement of MXene‐based flexible piezoresistive sensors in future are also discussed, which will revolutionize the sensing field and offer a wealth of opportunities in biomedicine and beyond.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

Recent Advances in Multi‐Scale Piezoresistive Interfaces for MXene‐Based Flexible Sensors

Ge,

Sun,

Huang

et al. 2024

Adv Materials Technologies

View full text Add to dashboard Cite

show abstract

“…EasyJet provides travel recommendations based on previous trips, while Twiddy offers rental pricing suggestions based on demand trends. Microsoft Dynamics 365 uses advanced AI in NLP to assist customer service agents and managers make better decisions, providing data insights to enhance customer engagement (Wei et al, 2023).…”

Section: Literature Reviewmentioning

confidence: 99%

Enhancing Customer Service in Shopping Malls with an Advanced Chatbot-Integrated Concierge Device

Maj,

Dmowski,

Nowak

et al. 2024

ERSJ

View full text Add to dashboard Cite

Purpose:The primary objective of this study is to enhance customer service in shopping malls by introducing an innovative solution: a Concierge device equipped with an advanced chatbot assistant. The aim is to simplify mall navigation for customers by offering information on store locations, services, promotions, and events. Design/Methodology/Approach: The Concierge device features a monitor displaying an interactive mall map that users can navigate to find store details, locations, and opening hours. A chatbot integrated with the device provides a personalized shopping experience, recognizing customers via onboard cameras and adjusting interactions based on their emotions. The device also visualizes routes to stores and highlights promotions along the way. Key services such as toilets and ATMs are easily located through the device, which uses the chatbot to suggest nearby points. Findings: Preliminary research indicates that this advanced assistant enhances the customer shopping experience by providing tailored information and seamless navigation. The device effectively routes users to destinations while promoting additional services and events, ultimately improving shopping mall service efficiency. Practical Implications: Implementing this Concierge device in shopping malls can significantly improve customer satisfaction by providing accurate, real-time information and personalized guidance. Retailers and service providers can expect increased customer engagement and better promotion of their products and services through this system. Originality/Value: This solution integrates state-of-the-art emotion recognition and chatbot technology with interactive maps, offering a unique and innovative approach to shopping mall navigation. By providing personalized service and improving customer engagement, it adds significant value to the current shopping mall customer service landscape.

show abstract

Implicit Perception of Differences between NLP‐Produced and Human‐Produced Language in the Mentalizing Network

et al. 2023

Self Cite

View full text Add to dashboard Cite

Natural language processing (NLP) is central to the communication with machines and among ourselves, and NLP research field has long sought to produce human‐quality language. Identification of informative criteria for measuring NLP‐produced language quality will support development of ever‐better NLP tools. The authors hypothesize that mentalizing network neural activity may be used to distinguish NLP‐produced language from human‐produced language, even for cases where human judges cannot subjectively distinguish the language source. Using the social chatbots Google Meena in English and Microsoft XiaoIce in Chinese to generate NLP‐produced language, behavioral tests which reveal that variance of personality perceived from chatbot chats is larger than for human chats are conducted, suggesting that chatbot language usage patterns are not stable. Using an identity rating task with functional magnetic resonance imaging, neuroimaging analyses which reveal distinct patterns of brain activity in the mentalizing network including the DMPFC and rTPJ in response to chatbot versus human chats that cannot be distinguished subjectively are conducted. This study illustrates a promising empirical basis for measuring the quality of NLP‐produced language: adding a judge's implicit perception as an additional criterion.

show abstract

Implicit Perception of Differences between NLP‐Produced and Human‐Produced Language in the Mentalizing Network

Cited by 4 publications

References 67 publications

Recent Advances in Multi‐Scale Piezoresistive Interfaces for MXene‐Based Flexible Sensors

Recent Advances in Multi‐Scale Piezoresistive Interfaces for MXene‐Based Flexible Sensors

Enhancing Customer Service in Shopping Malls with an Advanced Chatbot-Integrated Concierge Device

Implicit Perception of Differences between NLP‐Produced and Human‐Produced Language in the Mentalizing Network

Contact Info

Product

Resources

About