Utilizing Instagram Data to Identify Usage Patterns Associated With Schizophrenia Spectrum Disorders
Background and Objectives: Prior research has successfully identified linguistic and behavioral patterns associated with schizophrenia spectrum disorders (SSD) from user generated social media activity. Few studies, however, have explored the potential for image analysis to inform psychiatric care f...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-08-01
|
| Series: | Frontiers in Psychiatry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyt.2021.691327/full |
| _version_ | 1819081616940597248 |
|---|---|
| author | Katrin Hänsel Katrin Hänsel Katrin Hänsel Inna Wanyin Lin Michael Sobolev Michael Sobolev Michael Sobolev Whitney Muscat Sabrina Yum-Chan Sabrina Yum-Chan Munmun De Choudhury John M. Kane John M. Kane John M. Kane Michael L. Birnbaum Michael L. Birnbaum Michael L. Birnbaum |
| author_facet | Katrin Hänsel Katrin Hänsel Katrin Hänsel Inna Wanyin Lin Michael Sobolev Michael Sobolev Michael Sobolev Whitney Muscat Sabrina Yum-Chan Sabrina Yum-Chan Munmun De Choudhury John M. Kane John M. Kane John M. Kane Michael L. Birnbaum Michael L. Birnbaum Michael L. Birnbaum |
| author_sort | Katrin Hänsel |
| collection | DOAJ |
| description | Background and Objectives: Prior research has successfully identified linguistic and behavioral patterns associated with schizophrenia spectrum disorders (SSD) from user generated social media activity. Few studies, however, have explored the potential for image analysis to inform psychiatric care for individuals with SSD. Given the popularity of image-based platforms, such as Instagram, investigating user generated image data could further strengthen associations between social media activity and behavioral health.Methods: We collected 11,947 Instagram posts across 68 participants (mean age = 23.6; 59% male) with schizophrenia spectrum disorders (SSD; n = 34) and healthy volunteers (HV; n = 34). We extracted image features including color composition, aspect ratio, and number of faces depicted. Additionally, we considered social connections and behavioral features. We explored differences in usage patterns between SSD and HV participants.Results: Individuals with SSD posted images with lower saturation (p = 0.033) and lower colorfulness (p = 0.005) compared to HVs, as well as images showing fewer faces on average (SSD = 1.5, HV = 2.4, p < 0.001). Further, individuals with SSD demonstrated a lower ratio of followers to following compared to HV participants (p = 0.025).Conclusion: Differences in uploaded images and user activity on Instagram were identified in individuals with SSD. These differences highlight potential digital biomarkers of SSD from Instagram data. |
| first_indexed | 2024-12-21T20:03:37Z |
| format | Article |
| id | doaj.art-9edb12555c7b4f0b9460a3a6b5bd06c1 |
| institution | Directory Open Access Journal |
| issn | 1664-0640 |
| language | English |
| last_indexed | 2024-12-21T20:03:37Z |
| publishDate | 2021-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychiatry |
| spelling | doaj.art-9edb12555c7b4f0b9460a3a6b5bd06c12022-12-21T18:51:55ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402021-08-011210.3389/fpsyt.2021.691327691327Utilizing Instagram Data to Identify Usage Patterns Associated With Schizophrenia Spectrum DisordersKatrin Hänsel0Katrin Hänsel1Katrin Hänsel2Inna Wanyin Lin3Michael Sobolev4Michael Sobolev5Michael Sobolev6Whitney Muscat7Sabrina Yum-Chan8Sabrina Yum-Chan9Munmun De Choudhury10John M. Kane11John M. Kane12John M. Kane13Michael L. Birnbaum14Michael L. Birnbaum15Michael L. Birnbaum16The Zucker Hillside Hospital, Northwell Health, Glen Oaks, NY, United StatesFeinstein Institute for Medical Research, Northwell Health, Manhasset, NY, United StatesCornell Tech, Cornell University, New York, NY, United StatesCornell Tech, Cornell University, New York, NY, United StatesThe Zucker Hillside Hospital, Northwell Health, Glen Oaks, NY, United StatesFeinstein Institute for Medical Research, Northwell Health, Manhasset, NY, United StatesCornell Tech, Cornell University, New York, NY, United StatesDepartment of Psychology, Hofstra University, Hempstead, NY, United StatesThe Zucker Hillside Hospital, Northwell Health, Glen Oaks, NY, United StatesFeinstein Institute for Medical Research, Northwell Health, Manhasset, NY, United StatesSchool of Interactive Computing, Georgia Institute of Technology, Atlanta, GA, United StatesThe Zucker Hillside Hospital, Northwell Health, Glen Oaks, NY, United StatesFeinstein Institute for Medical Research, Northwell Health, Manhasset, NY, United StatesDonald and Barbara Zucker School of Medicine at Hofstra/Northwell, Hampstead, NY, United StatesThe Zucker Hillside Hospital, Northwell Health, Glen Oaks, NY, United StatesFeinstein Institute for Medical Research, Northwell Health, Manhasset, NY, United StatesDonald and Barbara Zucker School of Medicine at Hofstra/Northwell, Hampstead, NY, United StatesBackground and Objectives: Prior research has successfully identified linguistic and behavioral patterns associated with schizophrenia spectrum disorders (SSD) from user generated social media activity. Few studies, however, have explored the potential for image analysis to inform psychiatric care for individuals with SSD. Given the popularity of image-based platforms, such as Instagram, investigating user generated image data could further strengthen associations between social media activity and behavioral health.Methods: We collected 11,947 Instagram posts across 68 participants (mean age = 23.6; 59% male) with schizophrenia spectrum disorders (SSD; n = 34) and healthy volunteers (HV; n = 34). We extracted image features including color composition, aspect ratio, and number of faces depicted. Additionally, we considered social connections and behavioral features. We explored differences in usage patterns between SSD and HV participants.Results: Individuals with SSD posted images with lower saturation (p = 0.033) and lower colorfulness (p = 0.005) compared to HVs, as well as images showing fewer faces on average (SSD = 1.5, HV = 2.4, p < 0.001). Further, individuals with SSD demonstrated a lower ratio of followers to following compared to HV participants (p = 0.025).Conclusion: Differences in uploaded images and user activity on Instagram were identified in individuals with SSD. These differences highlight potential digital biomarkers of SSD from Instagram data.https://www.frontiersin.org/articles/10.3389/fpsyt.2021.691327/fullserious mental illnessschizophrenia spectrum disordersocial media markersdigital biomarkersimage analysis |
| spellingShingle | Katrin Hänsel Katrin Hänsel Katrin Hänsel Inna Wanyin Lin Michael Sobolev Michael Sobolev Michael Sobolev Whitney Muscat Sabrina Yum-Chan Sabrina Yum-Chan Munmun De Choudhury John M. Kane John M. Kane John M. Kane Michael L. Birnbaum Michael L. Birnbaum Michael L. Birnbaum Utilizing Instagram Data to Identify Usage Patterns Associated With Schizophrenia Spectrum Disorders Frontiers in Psychiatry serious mental illness schizophrenia spectrum disorder social media markers digital biomarkers image analysis |
| title | Utilizing Instagram Data to Identify Usage Patterns Associated With Schizophrenia Spectrum Disorders |
| title_full | Utilizing Instagram Data to Identify Usage Patterns Associated With Schizophrenia Spectrum Disorders |
| title_fullStr | Utilizing Instagram Data to Identify Usage Patterns Associated With Schizophrenia Spectrum Disorders |
| title_full_unstemmed | Utilizing Instagram Data to Identify Usage Patterns Associated With Schizophrenia Spectrum Disorders |
| title_short | Utilizing Instagram Data to Identify Usage Patterns Associated With Schizophrenia Spectrum Disorders |
| title_sort | utilizing instagram data to identify usage patterns associated with schizophrenia spectrum disorders |
| topic | serious mental illness schizophrenia spectrum disorder social media markers digital biomarkers image analysis |
| url | https://www.frontiersin.org/articles/10.3389/fpsyt.2021.691327/full |
| work_keys_str_mv | AT katrinhansel utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT katrinhansel utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT katrinhansel utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT innawanyinlin utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT michaelsobolev utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT michaelsobolev utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT michaelsobolev utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT whitneymuscat utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT sabrinayumchan utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT sabrinayumchan utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT munmundechoudhury utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT johnmkane utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT johnmkane utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT johnmkane utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT michaellbirnbaum utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT michaellbirnbaum utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders AT michaellbirnbaum utilizinginstagramdatatoidentifyusagepatternsassociatedwithschizophreniaspectrumdisorders |