Personalizing Affective Stimuli Using a Recommender Algorithm: An Example with Threatening Words for Trauma Exposed Populations
Experimental paradigms used in affective and clinical science often use stimuli such as images, scenarios, videos, or words to elicit emotional responses in study participants. Choosing appropriate stimuli that are highly evocative is essential to the study of emotional processes in both healthy and clinical populations. Selecting one set of stimuli that will be relevant for all subjects can be challenging because not every person responds the same way to a given stimulus. Machine learning can facilitate the personalization of such stimuli. The current study applied a novel statistical approach called a recommender algorithm to the selection of highly threatening words for a trauma-exposed population (N = 837). Participants rated 513 threatening words, and we trained a user–user collaborative filtering recommender algorithm. The algorithm uses similarities between individuals to predict ratings for unrated words. We compared threat ratings for algorithm-based word selection to a random word set, a word set previously used in research, and trauma-specific word sets. Algorithm-selected personalized words were more threatening compared to non-personalized words with large effects (ds = 2.10–2.92). Recommender algorithms can automate the personalization of stimuli from a large pool of possible stimuli to maximize emotional reactivity in research paradigms. These methods also hold potential for the personalization of behavioral treatments administered remotely where a provider is not available to tailor an intervention to the individual. The word personalization algorithm is available for use online (https://threat-word-predictor.herokuapp.com/).
KeywordsAnxiety Posttraumatic stress disorder Emotion Affect Recommender algorithm Trauma Personalization Personalized medicine
The current project was funded by the UCSF Digital Mental Health Resource Allocation Program. Dr. Niles is funded by the San Francisco VA Advanced Women’s Health Fellowship and Dr. O'Donovan is funded by a K01 Award from the National Institute of Mental Health (K01MH109871) and a University of California Hellman Award. We also acknowledge Vivien Li for her significant contributions during the data collection phase of this project.
Funding was provided by University of California, San Francisco (Grant No. 7710 133105 7500634 45), the San Francisco VA Advanced Women's Health Fellowship, a K01 Career Development Award (K01MH109871) and a University of California Hellman Award.
Compliance with Ethical Standards
Conflict of Interest
Drs. Niles and O’Donovan declare that they have no conflict of interest.
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Informed consent was obtained from all individual participants included in the study.
Animal Rights Statements
No animal studies were carried out by the authors for this article.
- Amir, N., Kuckertz, J. M., & Strege, M. V. (2016). A pilot study of an adaptive, idiographic, and multi-component attention bias modification program for social anxiety disorder. Cognitive Therapy and Research, 40(5), 661–671. https://doi.org/10.1007/s10608-016-9781-1.CrossRefPubMedPubMedCentralGoogle Scholar
- Bradley, M., & Lang, P. (1999). Affective norms for English words (ANEW): Instruction manual and affective ratings. Gainesville: University of FloridaGoogle Scholar
- Bunnell, S. (2007). The impact of abuse exposure on memory processes and attentional biases in a college-aged sample. Ann Arbor Dissertations & Theses.Google Scholar
- Carlson, E. B., Smith, S. R., Palmieri, P. A., Dalenberg, C., Ruzek, J. I., Kimerling, R., … Spain, D. A. (2011). Development and validation of a brief self-report measure of trauma exposure: The trauma history screen. Psychological Assessment, 23(2), 463–477. https://doi.org/10.1037/a0022294.CrossRefPubMedPubMedCentralGoogle Scholar
- Fridrici, C., Leichsenring-Driessen, C., Driessen, M., Wingenfeld, K., Kremer, G., & Beblo, T. (2013). The individualized alcohol Stroop task: No attentional bias toward personalized stimuli in alcohol-dependents. Psychology of Addictive Behaviors: Journal of the Society of Psychologists in Addictive Behaviors, 27(1), 62–70. https://doi.org/10.1037/a0029139.CrossRefGoogle Scholar
- Kilpatrick, D. G., Resnick, H. S., Milanak, M. E., Miller, M. W., Keyes, K. M., & Friedman, M. J. (2013). National estimates of exposure to traumatic events and PTSD prevalence using DSM-IV and DSM-5 criteria. Journal of Traumatic Stress, 26(5), 537–547. https://doi.org/10.1002/jts.21848.CrossRefPubMedPubMedCentralGoogle Scholar
- Lang, P. J., Bradley, M. M., & Cuthbert, B. N. (1999). International affective picture system (IAPS): Technical manual and affective ratings. Gainesville, FL: The Center for Research in Psychophysiology, University of Florida.Google Scholar
- MacLeod, C., Rutherford, E., Campbell, L., Ebsworthy, G., & Holker, L. (2002). Selective attention and emotional vulnerability: Assessing the causal basis of their association through the experimental manipulation of attentional bias. The Journal of Abnormal Psychology, 111(1), 107–123. https://doi.org/10.1037/0021-843X.111.1.107.CrossRefPubMedGoogle Scholar
- R Core Team. (2013). R: A language and environment for statistical computing. Vienna: R Development Core TeamGoogle Scholar
- Rashid, A. M., Albert, I., Cosley, D., Lam, S. K., McNee, S. M., Konstan, J. A., & Riedl, J. (2002). Getting to know you: Learning new user preferences in recommender systems. In Proceedings of the 7th international conference on intelligent user interfaces (pp. 127–134). New York, NY, USA: ACM. https://doi.org/10.1145/502716.502737.
- Schoorl, M., Putman, P., Mooren, T. M., Van Der Werff, S., & Van Der Does, W. (2014). Attentional bias modification in Dutch veterans with posttraumatic stress disorder: A case series with a personalized treatment version. Journal of Traumatic Stress, 27(2), 240–243. https://doi.org/10.1002/jts.21896.CrossRefPubMedGoogle Scholar
- Siegle, G. J., Steinhauer, S. R., Thase, M. E., Stenger, V. A., & Carter, C. S. (2002). Can’t shake that feeling: event-related fMRI assessment of sustained amygdala activity in response to emotional information in depressed individuals. Biological Psychiatry, 51(9), 693–707. https://doi.org/10.1016/S0006-3223(02)01314-8.CrossRefPubMedGoogle Scholar
- StataCorp. (2015). Stata statistical software: Release 14. College Station, TX: StataCorp LP.Google Scholar
- Swick, D. (2009). The separate and cumulative effects of TBI and PTSD on cognitive function and emotional control (Annual Report No. W81XWH-08-2-0086). Martinez, CA: Veterans Health Administration.Google Scholar