Loading...
Paper Type
Complete
Description
Research on the peer-to-peer (P2P) platforms, privacy, and digitalized business environment has overwhelmingly treated the intimacy of self-disclosure as a survey-based, subjective, and cognitive construct. A few studies have conducted topic analysis using objective data, but are still limited by the difficulty of capturing the degree of intimacy, which hinders the development of the transaction antecedents of P2P platforms. Building upon social penetration theory, we propose an innovative approach to identifying the intimacy of self-disclosure using a deep learning algorithm and an expert-compiled intimacy corpus in the context of P2P platforms. Adopting a sample dataset of 10,000 hosts’ self-descriptions in Airbnb, we introduce the computational and verification process of operationalizing the intimacy of self-disclosure. Through an empirical study, we demonstrate the theoretical feasibility of our quantification method of intimacy and show the potential of using deep learning to measure self-disclosure, expanding the theoretical development of social penetration theory and self-disclosure.
Paper Number
1466
Recommended Citation
Zhang, Xi; Qi, Chengzhu; Wei, Xin; and He, Wei, "Identifying Intimacy of Self-Disclosure: A Design Based on Social Penetration Theory and Deep Learning" (2023). AMCIS 2023 Proceedings. 7.
https://aisel.aisnet.org/amcis2023/sig_dsa/sig_dsa/7
Identifying Intimacy of Self-Disclosure: A Design Based on Social Penetration Theory and Deep Learning
Research on the peer-to-peer (P2P) platforms, privacy, and digitalized business environment has overwhelmingly treated the intimacy of self-disclosure as a survey-based, subjective, and cognitive construct. A few studies have conducted topic analysis using objective data, but are still limited by the difficulty of capturing the degree of intimacy, which hinders the development of the transaction antecedents of P2P platforms. Building upon social penetration theory, we propose an innovative approach to identifying the intimacy of self-disclosure using a deep learning algorithm and an expert-compiled intimacy corpus in the context of P2P platforms. Adopting a sample dataset of 10,000 hosts’ self-descriptions in Airbnb, we introduce the computational and verification process of operationalizing the intimacy of self-disclosure. Through an empirical study, we demonstrate the theoretical feasibility of our quantification method of intimacy and show the potential of using deep learning to measure self-disclosure, expanding the theoretical development of social penetration theory and self-disclosure.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
SIG DSA