Robert R. Morris

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 participant, but large differences across the participants. We examined two ways to address the individual differences to automatically 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 person, and of 73.41% when trained and tested on different people using the proposed adaptations to SVMs.

Efficacy of a Web-based, crowdsourced peer-to-peer cognitive reappraisal platform for depression: randomized controlled trial.

Background Self-guided, Web-based interventions for depression show promising results but suffer from high attrition and low user engagement. Online peer support networks can be highly engaging, but they show mixed results and lack evidence-based content. Objective Our aim was to introduce and evaluate a novel Web-based, peer-to-peer cognitive reappraisal platform designed to promote evidence-based techniques, with the hypotheses that (1) repeated use of the platform increases reappraisal and reduces depression and (2) that the social, crowdsourced interactions enhance engagement. Methods Participants aged 18-35 were recruited online and were randomly assigned to the treatment group, “Panoply” (n=84), or an active control group, online expressive writing (n=82). Both are fully automated Web-based platforms. Participants were asked to use their assigned platform for a minimum of 25 minutes per week for 3 weeks. Both platforms involved posting descriptions of stressful thoughts and situations. Participants on the Panoply platform additionally received crowdsourced reappraisal support immediately after submitting a post (median response time=9 minutes). Panoply participants could also practice reappraising stressful situations submitted by other users. Online questionnaires administered at baseline and 3 weeks assessed depression symptoms, reappraisal, and perseverative thinking. Engagement was assessed through self-report measures, session data, and activity levels. Results The Panoply platform produced significant improvements from pre to post for depression (P=.001), reappraisal (P<.001), and perseverative thinking (P<.001). The expressive writing platform yielded significant pre to post improvements for depression (P=.02) and perseverative thinking (P<.001), but not reappraisal (P=.45). The two groups did not diverge significantly at post-test on measures of depression or perseverative thinking, though Panoply users had significantly higher reappraisal scores (P=.02) than expressive writing. We also found significant group by treatment interactions. Individuals with elevated depression symptoms showed greater comparative benefit from Panoply for depression (P=.02) and perseverative thinking (P=.008). Individuals with baseline reappraisal deficits showed greater comparative benefit from Panoply for depression (P=.002) and perseverative thinking (P=.002). Changes in reappraisal mediated the effects of Panoply, but not the expressive writing platform, for both outcomes of depression (ab=-1.04, SE 0.58, 95% CI -2.67 to -.12) and perseverative thinking (ab=-1.02, SE 0.61, 95% CI -2.88 to -.20). Dropout rates were similar for the two platforms; however, Panoply yielded significantly more usage activity (P<.001) and significantly greater user experience scores (P<.001). Conclusions Panoply engaged its users and was especially helpful for depressed individuals and for those who might ordinarily underutilize reappraisal techniques. Further investigation is needed to examine the long-term effects of such a platform and whether the benefits generalize to a more diverse population of users. Trial Registration ClinicalTrials.gov NCT02302248; https://clinicaltrials.gov/ct2/show/NCT02302248 (Archived by WebCite at http://www.webcitation.org/6Wtkj6CXU).

Priming for Better Performance in Microtask Crowdsourcing Environments

Although microtask platforms are desirable for their speed, scalability, and low cost, task performance varies greatly. Many researchers have focused on improving the quality of the work performed on such platforms. Priming uses implicit mechanisms to induce observable changes in behavior. Although priming has been effective in the laboratory, its use hasnt been explored extensively in software design, perhaps because the effects are often short-lived. In the context of microtask crowdsourcing environments, however, where tasks are short and circumscribed, temporary priming effects can lead to significant performance gains.

Combining crowdsourcing and learning to improve engagement and performance

Crowdsourcing complex creative tasks remains difficult, in part because these tasks require skilled workers. Most crowdsourcing platforms do not help workers acquire the skills necessary to accomplish complex creative tasks. In this paper, we describe a platform that combines learning and crowdsourcing to benefit both the workers and the requesters. Workers gain new skills through interactive step-by-step tutorials and test their knowledge by improving real-world images submitted by requesters. In a series of three deployments spanning two years, we varied the design of our platform to enhance the learning experience and improve the quality of the crowd work. We tested our approach in the context of LevelUp for Photoshop, which teaches people how to do basic photograph improvement tasks using Adobe Photoshop. We found that by using our system workers gained new skills and produced high-quality edits for requested images, even if they had little prior experience editing images.

Broadening accessibility through special interests: a new approach for software customization

Individuals diagnosed with autism spectrum disorder (ASD) often fixate on narrow, restricted interests. These interests can be highly motivating, but they can also create attentional myopia, preventing individuals from pursuing a broad range of activities. Interestingly, researchers have found that preferred interests can be used to help individuals with ASD branch out and participate in educational, therapeutic, or social situations they might otherwise shun. When interventions are modified, such that an individuals interest is properly represented, task adherence and performance can increase. While this strategy has seen success in the research literature, it is difficult to implement on a large scale and therefore has not been widely adopted. This paper describes a software approach designed to solve this problem. The approach facilitates customization, allowing users to easily embed images of almost any special interest into computer-based interventions. Specifically, we describe an algorithm that will: (1) retrieve any image from the Google image database; (2) strip it of its background; and (3) embed it seamlessly into Flash-based computer programs. To evaluate our algorithm, we employed it in a naturalistic setting with eleven individuals (nine diagnosed with ASD and two diagnosed with other developmental disorders). We also tested its ability to retrieve and process examples of preferred interests previously reported in the ASD literature. The results indicate that our method was an easy and efficient way for users to customize our software programs. While we believe this model is uniquely suited for individuals with ASD, we also foresee this approach being useful for anyone that might like a quick and simple way to personalize software programs.

Affect and Creative Performance on Crowdsourcing Platforms

Performance on crowd sourcing platforms varies greatly, especially for tasks requiring significant cognitive effort or creative insight. Researchers have proposed several techniques to address these problems, yet few have considered the role of affect, despite the well-established link between positive affect and creative performance. In this paper, we examine two affective techniques to boost creativity on crowd sourcing platforms - affective priming and affective pre-screening. Across three experiments, we find divergent results, depending on which technique is used. We find that not all happy crowd workers are alike. Those that are primed to feel happy exhibit enhanced creative performance, whereas those that merely report feeling happy exhibit impaired creative performance. We examine these findings in light of preexisting research on creativity, affect, and mood saliency. Lastly, we show how our findings have implications not only for crowd sourcing platforms, but also for other human-computer interaction scenarios that involve affect and creative performance.

Crowd-powered positive psychological interventions

Recent advances in crowdsourcing have led to new forms of assistive technologies, commonly referred to as crowd-powered devices. To best serve the user, these technologies crowdsource human intelligence as needed, when automated methods alone are insufficient. In this paper, we provide an overview of how these systems work and how they can be used to enhance technological interventions for positive psychology. As a specific example, we describe previous work that crowdsources positive reappraisals, providing users timely and personalized suggestions for ways to reconstrue stressful thoughts and situations. We then describe how this approach could be extended for use with other positive psychological interventions. Finally, we outline future directions for crowd-powered positive psychological interventions.

Helping Others Regulate Emotion Predicts Increased Regulation of One’s Own Emotions and Decreased Symptoms of Depression:

Although much research considers how individuals manage their own emotions, less is known about the emotional benefits of regulating the emotions of others. We examined this topic in a 3-week study of an online platform providing training and practice in the social regulation of emotion. We found that participants who engaged more by helping others (vs. sharing and receiving support for their own problems) showed greater decreases in depression, mediated by increased use of reappraisal in daily life. Moreover, social regulation messages with more other-focused language (i.e., second-person pronouns) were (a) more likely to elicit expressions of gratitude from recipients and (b) predictive of increased use of reappraisal over time for message composers, suggesting perspective-taking enhances the benefits of practicing social regulation. These findings unpack potential mechanisms of socially oriented training in emotion regulation and suggest that by helping others regulate, we may enhance our own regulatory skills and emotional well-being.

Lessons learned from a pilot study quantifying face contact and skin conductance in teens with asperger syndrome

This paper presents lessons learned from a preliminary study quantifying face contact and corresponding physiological reactivity in teenagers with Asperger syndrome. In order to detect face contact and physiological arousability, we created a wearable system that combines a camera with OpenCV face detection and skin conductance sensors. In this paper, we discuss issues involved in setting up experimental environments for wearable platforms to detect face contact and skin conductance levels simultaneously, and address technological, statistical, and ethical considerations for future technological interventions.

Towards an Artificially Empathic Conversational Agent for Mental Health Applications: System Design and User Perceptions

Background Conversational agents cannot yet express empathy in nuanced ways that account for the unique circumstances of the user. Agents that possess this faculty could be used to enhance digital mental health interventions. Objective We sought to design a conversational agent that could express empathic support in ways that might approach, or even match, human capabilities. Another aim was to assess how users might appraise such a system. Methods Our system used a corpus-based approach to simulate expressed empathy. Responses from an existing pool of online peer support data were repurposed by the agent and presented to the user. Information retrieval techniques and word embeddings were used to select historical responses that best matched a user’s concerns. We collected ratings from 37,169 users to evaluate the system. Additionally, we conducted a controlled experiment (N=1284) to test whether the alleged source of a response (human or machine) might change user perceptions. Results The majority of responses created by the agent (2986/3770, 79.20%) were deemed acceptable by users. However, users significantly preferred the efforts of their peers (P<.001). This effect was maintained in a controlled study (P=.02), even when the only difference in responses was whether they were framed as coming from a human or a machine. Conclusions Our system illustrates a novel way for machines to construct nuanced and personalized empathic utterances. However, the design had significant limitations and further research is needed to make this approach viable. Our controlled study suggests that even in ideal conditions, nonhuman agents may struggle to express empathy as well as humans. The ethical implications of empathic agents, as well as their potential iatrogenic effects, are also discussed.