Computationally modeling interpersonal trust
We present a computational model capable of predicting—above human accuracy—the degree of trust a person has toward their novel partner by observing the trust-related nonverbal cues expressed in their social interaction. We summarize our prior work, in which we identify nonverbal cues that signal un...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Frontiers Research Foundation
2014
|
| Online Access: | http://hdl.handle.net/1721.1/85684 https://orcid.org/0000-0002-0587-2065 https://orcid.org/0000-0003-1175-437X |
| _version_ | 1811086302719770624 |
|---|---|
| author | Lee, Jin Joo Wormwood, Jolie B. DeSteno, David Breazeal, Cynthia Lynn Knox, Brad |
| author2 | Massachusetts Institute of Technology. Media Laboratory |
| author_facet | Massachusetts Institute of Technology. Media Laboratory Lee, Jin Joo Wormwood, Jolie B. DeSteno, David Breazeal, Cynthia Lynn Knox, Brad |
| author_sort | Lee, Jin Joo |
| collection | MIT |
| description | We present a computational model capable of predicting—above human accuracy—the degree of trust a person has toward their novel partner by observing the trust-related nonverbal cues expressed in their social interaction. We summarize our prior work, in which we identify nonverbal cues that signal untrustworthy behavior and also demonstrate the human mind's readiness to interpret those cues to assess the trustworthiness of a social robot. We demonstrate that domain knowledge gained from our prior work using human-subjects experiments, when incorporated into the feature engineering process, permits a computational model to outperform both human predictions and a baseline model built in naiveté of this domain knowledge. We then present the construction of hidden Markov models to investigate temporal relationships among the trust-related nonverbal cues. By interpreting the resulting learned structure, we observe that models built to emulate different levels of trust exhibit different sequences of nonverbal cues. From this observation, we derived sequence-based temporal features that further improve the accuracy of our computational model. Our multi-step research process presented in this paper combines the strength of experimental manipulation and machine learning to not only design a computational trust model but also to further our understanding of the dynamics of interpersonal trust. |
| first_indexed | 2024-09-23T13:23:43Z |
| format | Article |
| id | mit-1721.1/85684 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T13:23:43Z |
| publishDate | 2014 |
| publisher | Frontiers Research Foundation |
| record_format | dspace |
| spelling | mit-1721.1/856842022-09-28T13:53:29Z Computationally modeling interpersonal trust Lee, Jin Joo Wormwood, Jolie B. DeSteno, David Breazeal, Cynthia Lynn Knox, Brad Massachusetts Institute of Technology. Media Laboratory Program in Media Arts and Sciences (Massachusetts Institute of Technology) Lee, Jin Joo Knox, William Bradley Breazeal, Cynthia Lynn We present a computational model capable of predicting—above human accuracy—the degree of trust a person has toward their novel partner by observing the trust-related nonverbal cues expressed in their social interaction. We summarize our prior work, in which we identify nonverbal cues that signal untrustworthy behavior and also demonstrate the human mind's readiness to interpret those cues to assess the trustworthiness of a social robot. We demonstrate that domain knowledge gained from our prior work using human-subjects experiments, when incorporated into the feature engineering process, permits a computational model to outperform both human predictions and a baseline model built in naiveté of this domain knowledge. We then present the construction of hidden Markov models to investigate temporal relationships among the trust-related nonverbal cues. By interpreting the resulting learned structure, we observe that models built to emulate different levels of trust exhibit different sequences of nonverbal cues. From this observation, we derived sequence-based temporal features that further improve the accuracy of our computational model. Our multi-step research process presented in this paper combines the strength of experimental manipulation and machine learning to not only design a computational trust model but also to further our understanding of the dynamics of interpersonal trust. National Science Foundation (U.S.) (Research Grant CCF-1138986) National Science Foundation (U.S.) (Research Grant BCS-0827084) 2014-03-17T19:04:35Z 2014-03-17T19:04:35Z 2013-12 2013-07 Article http://purl.org/eprint/type/JournalArticle 1664-1078 http://hdl.handle.net/1721.1/85684 Lee, Jin Joo, W. Bradley Knox, Jolie B. Wormwood, Cynthia Breazeal, and David DeSteno. “Computationally Modeling Interpersonal Trust.” Front. Psychol. 4 (2013). https://orcid.org/0000-0002-0587-2065 https://orcid.org/0000-0003-1175-437X en_US http://dx.doi.org/10.3389/fpsyg.2013.00893 Frontiers in Psychology Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Frontiers Research Foundation Frontiers |
| spellingShingle | Lee, Jin Joo Wormwood, Jolie B. DeSteno, David Breazeal, Cynthia Lynn Knox, Brad Computationally modeling interpersonal trust |
| title | Computationally modeling interpersonal trust |
| title_full | Computationally modeling interpersonal trust |
| title_fullStr | Computationally modeling interpersonal trust |
| title_full_unstemmed | Computationally modeling interpersonal trust |
| title_short | Computationally modeling interpersonal trust |
| title_sort | computationally modeling interpersonal trust |
| url | http://hdl.handle.net/1721.1/85684 https://orcid.org/0000-0002-0587-2065 https://orcid.org/0000-0003-1175-437X |
| work_keys_str_mv | AT leejinjoo computationallymodelinginterpersonaltrust AT wormwoodjolieb computationallymodelinginterpersonaltrust AT destenodavid computationallymodelinginterpersonaltrust AT breazealcynthialynn computationallymodelinginterpersonaltrust AT knoxbrad computationallymodelinginterpersonaltrust |