Human activities can be recognized in sensor data using supervised machine learning algorithms. In this approach, human annotators must annotate events in the sensor data which are used as input to supervised learning algorithms. Annotating events directly in time series graphs of data streams is difficult. Video is often collected and synchronized to the sensor data to aid human annotators in identifying events in the data. Other work in human activity recognition (HAR) minimizes the cost of annotation by using unsupervised or semi-supervised machine learning algorithms or using algorithms that are more tolerant of human annotation errors. Rather than adjusting algorithms, we focus on the performance of the human annotators themselves. Understanding how human annotators perform annotation may lead to annotation interfaces and data collection schemes that better support annotators. We investigate the accuracy and efficiency of human annotators in the context of four HAR tasks when using video, data, or both to annotate events. After a training period, we found that annotators were more efficient when using data alone on three of four tasks and more accurate when marking event types when using video alone on all four tasks. Annotators were more accurate when marking event boundaries using data alone on two tasks and more accurate using video alone on the other two tasks. Our results suggest that data and video collected for annotation of HAR tasks play different roles in the annotation process and these roles may vary with the HAR task.

About 18% of children in industrialized countries suffer from anxiety. We designed a mobile neurofeedback app, called Mind-Full, based on existing design guidelines. Our goal was for young children in lower socio-economic status schools to improve their ability to self-regulate anxiety by using Mind-Full. In this paper we report on quantitative outcomes from a sixteen-week field evaluation with 20 young children (aged 5 to 8). Our methodological contribution includes using a control group, validated measures of anxiety and stress, and assessing transfer and maintenance. Results from teacher and parent behavioral surveys indicated gains in children's ability to self-regulate anxiety at school and home; a decrease in anxious behaviors at home; and cortisol tests showed variable improvement in physiological stress levels. We contribute to HCI for mental health with evidence that it is viable to use a mobile app in lower socio-economic status schools to improve children's mental health.

To better understand the issues designers face as they interact with developers and use developer tools to create websites, we conducted a formative investigation consisting of interviews, a survey, and an analysis of professional design documents. Based on insights gained from these efforts, we developed Poirot, a web inspection tool for designers that enables them to make style edits to websites using a familiar graphical interface. We compared Poirot to Chrome DevTools in a lab study with 16 design professionals. We observed common problems designers experience when using Chrome DevTools and found that when using Poirot, designers were more successful in accomplishing typical design tasks (97% to 63%). In addition, we found that Poirot had a significantly lower perceived cognitive load and was overwhelmingly preferred by the designers in our study.

This Research Full Paper provides a review of literature regarding the participation of women in Computer Science (CS) related disciplines and discusses four different categories of variables, with the goal of determining what current professors, staff, and students can do to promote the retention and inclusion of female students in CS programs.1)Static attributes of female students (race, socioeconomic background, GPA, ACT/SAT score, etc).2)Adjustable attributes of the female students themselves (qualities that could be changed through workshops, courses, mentoring, or other training programs).3)Static attributes of the environment around female students (location of a university, number of students enrolled, etc).4)Adjustable attributes of the environments around female students (aspects of a program or university like what courses are required and in what order, who is teaching, what they are teaching, how they are teaching, etc).We review literature that suggests departments can attempt to influence attributes of the female students themselves, like students' self efficacy, thinking habits, and academic goals, through courses and programs. We conclude that this category of variables could be split into two ill-defined subcategories. First, variables which may be ethical to adjust, like students' confidence or self efficacy. Second, variables which may be better left unchanged: we note that if interventions lead female students to be more like their male peers, we are not attaining true diversity. We discuss the implications of attempting to change female students and discuss the effectiveness of modifying environments around female students.We take the position that the study of static attributes, whether internal or external to female students, leads to few actionable tasks. We propose that future research should look for adjustable factors that allow for professors, staff, and students to change their actions in order to increase retention rates.

This Research Full Paper presents the results of a longitudinal study about confidence and academic performance conducted at a large, R1, university over the course of a semester. We surveyed male (N = 226) and female (N = 67) students six times throughout the course of the semester and once after final grades were released. Each time, we asked students four questions designed to gauge students' overall confidence. Using a modified latent growth curve analysis, we found distinctively different patterns in confidence trajectories between students in CS-1, CS-2, CS-3, and CS-4; the four consecutive introductory courses. We found that students' confidence tended to show a significant decrease across all confidence variables for all four courses, though some courses showed a stronger decrease than others. We found a similar decline pattern for gender such that males initially reported higher confidence than females, but also showed a steeper decrease in confidence after receiving final grades. This declining trend was also predicted by grades, such that individuals who earned higher grades at the end of the semester initially began the semester with higher confidence, but these individuals also showed a steeper decrease in confidence after receiving their final grades. This work has implications for researchers interested in developing interventions designed to help students gain confidence when they need it most and for those interested in the relationship between confidence and retention.

Millions of children have challenges with anxiety that negatively impact their development, education and well-being. To address this challenge, we developed version 2.0 of Mind-Full, a wearable, mobile neurofeedback system, designed to teach young children to learn to self-regulate anxiety. We present a mixed methods evaluation of a seven week long intervention in schools. We report on a subset of outcome measures related to 10 children's anxiety and stress in the classroom and describe mediating socio-technological processes that may have impacted outcomes. Findings showed improvement in children's ability to self-regulate anxiety and reduced cortisol levels for some children. Qualitative findings suggested that children who made multimodal connections during system mediated learning and had teacher support for learning transfer responded well to the intervention. We suggest that framing mental health app design as a distributed, adaptive, socio-technological system enables designers to better meet individual's unique and changing mental health needs.