Sara L. Johansen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sara L. Johansen has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Alon Halevy
Google Cloud, Sunnyvale, USA
1 shared publication - Amar Ashar
Spotify Inc., New York City, USA
1 shared publication - Amy Xian Zhang
CSE, University of Washington, Seattle, Washington, USA
1 shared publication Ben A. Stenhaug
Stanford University Graduate School of Education, Stanford, California, USA
1 shared publication- Chloe Bakalar
Meta Inc., Menlo Park, USA
1 shared publication - Claire R. Leibowicz
Oxford Internet Institute University of Oxford Oxford UK
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 5 June 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
- Vol. 2 (3) , 1-57
Building Human Values into Recommender Systems: An Interdisciplinary Synthesis
Recommender systems are the algorithms which select, filter, and personalize content across many of the world's largest platforms and apps. As such, their positive and negative effects on individuals and on societies have been extensively theorized and studied. Our overarching question is how to ensure that recommender systems enact the values of the individuals and societies that they serve. Addressing this question in a principled fashion requires technical knowledge of recommender design and operation, and also critically depends on insights from diverse fields including social science, ethics, economics, psychology, policy, and law. This article is a multidisciplinary effort to synthesize theory and practice from different perspectives, with the goal of providing a shared language, articulating current design approaches, and identifying open problems. We collect a set of values that seem most relevant to recommender systems operating across different domains, and then examine them from the perspectives of current industry practice, measurement, product design, and policy approaches. Important open problems include multi-stakeholder processes for defining values and resolving trade-offs, better values-driven measurements, recommender controls that people use, non-behavioral algorithmic feedback, optimization for long-term outcomes, causal inference of recommender effects, academic-industry research collaborations, and interdisciplinary policy-making.
- 5 June 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
- Vol. 2 (3) , 1-57
Top Cited PapersOpen AccessBuilding Human Values into Recommender Systems: An Interdisciplinary Synthesis
Recommender systems are the algorithms which select, filter, and personalize content across many of the world's largest platforms and apps. As such, their positive and negative effects on individuals and on societies have been extensively theorized and studied. Our overarching question is how to ensure that recommender systems enact the values of the individuals and societies that they serve. Addressing this question in a principled fashion requires technical knowledge of recommender design and operation, and also critically depends on insights from diverse fields including social science, ethics, economics, psychology, policy, and law. This article is a multidisciplinary effort to synthesize theory and practice from different perspectives, with the goal of providing a shared language, articulating current design approaches, and identifying open problems. We collect a set of values that seem most relevant to recommender systems operating across different domains, and then examine them from the perspectives of current industry practice, measurement, product design, and policy approaches. Important open problems include multi-stakeholder processes for defining values and resolving trade-offs, better values-driven measurements, recommender controls that people use, non-behavioral algorithmic feedback, optimization for long-term outcomes, causal inference of recommender effects, academic-industry research collaborations, and interdisciplinary policy-making.
- 10 May 2022
- Published by Springer Nature in Journal of Technology in Behavioral Science
- Vol. 8 (4) , 336-340
Incorporating Digital Interventions into Mental Health Clinical Practice: a Pilot Survey of How Use Patterns, Barriers, and Opportunities Shifted for Clinicians in the COVID-19 Pandemic
Although many digital mental health interventions are available, clinicians do not routinely use them in clinical practice. In this pilot survey, we review the factors that supported the rapid transition to televisits during the COVID-19 pandemic, and we explore the barriers that continue to prevent clinicians from using other digital mental health interventions, such as mindfulness applications, mood trackers, and digital therapy programs. We conducted a pilot survey of mental health clinicians in different practice environments in the USA. Survey respondents (n = 51) were primarily psychiatrists working in academic medical centers. Results indicated that systemic factors, including workplace facilitation and insurance reimbursement, were primary reasons motivating clinicians to use televisits to provide remote patient care. The shift to televisits during the pandemic was not accompanied by increased use of other digital mental health interventions in patient care. Nine clinicians reported that they have never used digital interventions with patients. Among the 42 clinicians who did report some experience using digital interventions, the majority reported no change in the use of digital applications since transitioning to televisits. Our preliminary findings lend insight into the perspective of mental health clinicians regarding the factors that supported their transition to televisits, including institutional support and insurance reimbursement, and indicate that this shift to virtual patient care has not been accompanied by increased use of other digital mental health interventions. We contend that the same systemic factors that supported the shift toward virtual visits in the COVID-19 pandemic may be applied to support the incorporation of other digital interventions in mental healthcare.
- 10 May 2022
- Published by Springer Nature in Journal of Technology in Behavioral Science
- Vol. 8 (4) , 336-340
Incorporating Digital Interventions into Mental Health Clinical Practice: a Pilot Survey of How Use Patterns, Barriers, and Opportunities Shifted for Clinicians in the COVID-19 Pandemic
Although many digital mental health interventions are available, clinicians do not routinely use them in clinical practice. In this pilot survey, we review the factors that supported the rapid transition to televisits during the COVID-19 pandemic, and we explore the barriers that continue to prevent clinicians from using other digital mental health interventions, such as mindfulness applications, mood trackers, and digital therapy programs. We conducted a pilot survey of mental health clinicians in different practice environments in the USA. Survey respondents (n = 51) were primarily psychiatrists working in academic medical centers. Results indicated that systemic factors, including workplace facilitation and insurance reimbursement, were primary reasons motivating clinicians to use televisits to provide remote patient care. The shift to televisits during the pandemic was not accompanied by increased use of other digital mental health interventions in patient care. Nine clinicians reported that they have never used digital interventions with patients. Among the 42 clinicians who did report some experience using digital interventions, the majority reported no change in the use of digital applications since transitioning to televisits. Our preliminary findings lend insight into the perspective of mental health clinicians regarding the factors that supported their transition to televisits, including institutional support and insurance reimbursement, and indicate that this shift to virtual patient care has not been accompanied by increased use of other digital mental health interventions. We contend that the same systemic factors that supported the shift toward virtual visits in the COVID-19 pandemic may be applied to support the incorporation of other digital interventions in mental healthcare.
- 21 January 2020
- Published by Physicians Postgraduate Press, Inc in The Journal of Clinical Psychiatry
- Vol. 81 (1)
Past Psychiatric Conditions as Risk Factors for Postpartum Depression
What characteristics affect patients’ risk for postpartum depression? In what time frame is the risk greatest? Dr Johansen and colleagues analyzed a large US cohort to answer these questions. Find their results in this CME journal article.
- 21 January 2020
- Published by Physicians Postgraduate Press, Inc in The Journal of Clinical Psychiatry
- Vol. 81 (1)
Past Psychiatric Conditions as Risk Factors for Postpartum Depression
What characteristics affect patients’ risk for postpartum depression? In what time frame is the risk greatest? Dr Johansen and colleagues analyzed a large US cohort to answer these questions. Find their results in this CME journal article.
- 1 October 2017
- Published by Elsevier in Contraception
- Vol. 96 (4) , 248-253
Contraceptive counseling in reproductive-aged women treated for breast cancer at a tertiary care institution: a retrospective analysis
- 1 October 2017
- Published by Elsevier in Contraception
- Vol. 96 (4) , 248-253
Contraceptive counseling in reproductive-aged women treated for breast cancer at a tertiary care institution: a retrospective analysis