Call Center Stress Recognition with Person-Specific Models
Nine call center employees wore a skin conductance sensor on the wrist for a week at work and reported stress levels of each call. Although everyone had the same job profile, we found large differences in how individuals reported stress levels, with similarity from day to day within the same par...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Springer Berlin / Heidelberg
2011
|
| Online Access: | http://hdl.handle.net/1721.1/67691 https://orcid.org/0000-0002-5661-0022 https://orcid.org/0000-0001-9504-5217 |
| _version_ | 1811086874076250112 |
|---|---|
| author | Morris, Robert Randall Hernandez, Javier Picard, Rosalind W. |
| author2 | Massachusetts Institute of Technology. Media Laboratory |
| author_facet | Massachusetts Institute of Technology. Media Laboratory Morris, Robert Randall Hernandez, Javier Picard, Rosalind W. |
| author_sort | Morris, Robert Randall |
| collection | MIT |
| description | Nine call center employees wore a skin conductance sensor
on the wrist for a week at work and reported stress levels of each call.
Although everyone had the same job profile, we found large differences
in how individuals reported stress levels, with similarity from day to day
within the same participant, but large differences across the participants.
We examined two ways to address the individual differences to automat-
ically recognize classes of stressful/non-stressful calls, namely modifying
the loss function of Support Vector Machines (SVMs) to adapt to the
varying priors, and giving more importance to training samples from the
most similar people in terms of their skin conductance lability. We tested
the methods on 1500 calls and achieved an accuracy across participants
of 78.03% when trained and tested on different days from the same per-
son, and of 73.41% when trained and tested on different people using the
proposed adaptations to SVMs. |
| first_indexed | 2024-09-23T13:36:13Z |
| format | Article |
| id | mit-1721.1/67691 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T13:36:13Z |
| publishDate | 2011 |
| publisher | Springer Berlin / Heidelberg |
| record_format | dspace |
| spelling | mit-1721.1/676912022-10-01T15:57:23Z Call Center Stress Recognition with Person-Specific Models Morris, Robert Randall Hernandez, Javier Picard, Rosalind W. Massachusetts Institute of Technology. Media Laboratory Picard, Rosalind W. Morris, Robert Randall Picard, Rosalind W. Hernandez, Javier Nine call center employees wore a skin conductance sensor on the wrist for a week at work and reported stress levels of each call. Although everyone had the same job profile, we found large differences in how individuals reported stress levels, with similarity from day to day within the same participant, but large differences across the participants. We examined two ways to address the individual differences to automat- ically recognize classes of stressful/non-stressful calls, namely modifying the loss function of Support Vector Machines (SVMs) to adapt to the varying priors, and giving more importance to training samples from the most similar people in terms of their skin conductance lability. We tested the methods on 1500 calls and achieved an accuracy across participants of 78.03% when trained and tested on different days from the same per- son, and of 73.41% when trained and tested on different people using the proposed adaptations to SVMs. 2011-12-15T14:15:22Z 2011-12-15T14:15:22Z 2011-10 2011-10 Article http://purl.org/eprint/type/JournalArticle 978-3-642-24599-2 0302-9743 1611-3349 http://hdl.handle.net/1721.1/67691 Hernandez, Javier, Rob R. Morris, and Rosalind W. Picard. “Call Center Stress Recognition with Person-Specific Models.” Affective Computing and Intelligent Interaction. Ed. Sidney D’Mello et al. Vol. 6974. Berlin, Heidelberg: Springer Berlin Heidelberg, 2011. 125-134. https://orcid.org/0000-0002-5661-0022 https://orcid.org/0000-0001-9504-5217 en_US http://dx.doi.org/10.1007/978-3-642-24600-5_16 Affective Computing and Intelligent Interaction Creative Commons Attribution-Noncommercial-Share Alike 3.0 http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf Springer Berlin / Heidelberg Prof. Rosalind W. Picard |
| spellingShingle | Morris, Robert Randall Hernandez, Javier Picard, Rosalind W. Call Center Stress Recognition with Person-Specific Models |
| title | Call Center Stress Recognition with Person-Specific Models |
| title_full | Call Center Stress Recognition with Person-Specific Models |
| title_fullStr | Call Center Stress Recognition with Person-Specific Models |
| title_full_unstemmed | Call Center Stress Recognition with Person-Specific Models |
| title_short | Call Center Stress Recognition with Person-Specific Models |
| title_sort | call center stress recognition with person specific models |
| url | http://hdl.handle.net/1721.1/67691 https://orcid.org/0000-0002-5661-0022 https://orcid.org/0000-0001-9504-5217 |
| work_keys_str_mv | AT morrisrobertrandall callcenterstressrecognitionwithpersonspecificmodels AT hernandezjavier callcenterstressrecognitionwithpersonspecificmodels AT picardrosalindw callcenterstressrecognitionwithpersonspecificmodels |