Deconstructing Categorization in Visualization Recommendation: A Taxonomy and Comparative Study.

Visualization recommendation (VisRec) systems provide users with suggestions for potentially interesting and useful next steps during exploratory data analysis. These recommendations are typically organized into categories based on their analytical actions, i.e., operations employed to transition from the current exploration state to a recommended visualization. However, despite the emergence of a plethora of VisRec systems in recent work, the utility of the categories employed by these systems in analytical workflows has not been systematically investigated. Our article explores the efficacy of recommendation categories by formalizing a taxonomy of common categories and developing a system, Frontier, that implements these categories. Using Frontier, we evaluate workflow strategies adopted by users and how categories influence those strategies. Participants found recommendations that add attributes to enhance the current visualization and recommendations that filter to sub-populations to be comparatively most useful during data exploration. Our findings pave the way for next-generation VisRec systems that are adaptive and personalized via carefully chosen, effective recommendation categories.

Three Lessons from Accelerating Scientific Insight Discovery via Visual Querying.

Exploratory data analysis is a crucial part of data-driven scientific discovery. Yet, the process of discovering insights from visualization can be a manual and painstaking process. This article discusses some of the lessons we learned from working with scientists in designing visual data exploration system, along with design considerations for future tools.

You can't always sketch what you want: Understanding Sensemaking in Visual Query Systems.

Visual query systems (VQSs) empower users to interactively search for line charts with desired visual patterns, typically specified using intuitive sketch-based interfaces. Despite decades of past work on VQSs, these efforts have not translated to adoption in practice, possibly because VQSs are largely evaluated in unrealistic lab-based settings. To remedy this gap in adoption, we collaborated with experts from three diverse domains-astronomy, genetics, and material science-via a year-long user-centered design process to develop a VQS that supports their workflow and analytical needs, and evaluate how VQSs can be used in practice. Our study results reveal that ad-hoc sketch-only querying is not as commonly used as prior work suggests, since analysts are often unable to precisely express their patterns of interest. In addition, we characterize three essential sensemaking processes supported by our enhanced VQS. We discover that participants employ all three processes, but in different proportions, depending on the analytical needs in each domain. Our findings suggest that all three sensemaking processes must be integrated in order to make future VQSs useful for a wide range of analytical inquiries.

Acoustic correlates for perceived effort levels in male and female acted voices.

The best actors, particularly classic Shakespearian actors, are experts at vocal expression. With prosodic inflection, change of voice quality, and non-textual utterances, they communicate emotion, emphasize ideas, create drama, and form a complementary language which works with the text to tell the story in the script. To begin to study selected elements of vocal expression in acted speech, corpora were curated from male actors' Hamlet and female actresses' Lady Macbeth soliloquy performances. L1 speakers of American English on Mechanical Turk listened to excerpts from the corpora, and provided descriptions of the speaker's vocal expression. In this exploratory, open-ended, mixed-methods study, approximately 60% of all responses described emotion, and the remainder of responses split evenly between voice quality (including effort levels) and prosody. Also, significant differences were found in the kind and quantity of descriptors applied to male and female speech. Perception-grounded male and female acoustic feature sets which tracked the actors' expressive effort levels through the continuum of whispered, breathy, modal, and resonant speech are presented and validated via multiple models. The best results in applying these features to simple, un-optimized, four-way decision tree classifiers yielded 76% accuracy for male and 73% accuracy for female expressive, acted speech.

Parental Perceptions, Experiences, and Desires of Music Therapy.

Music therapy (MT) is a therapeutic practice where a therapist uses music to enhance the life quality for their patients. Children have an innate enjoyment of music, making music an effective medium for exploring their potential. In this study, we explore the parental perception of MT through an online survey. Contrary to the public perception that MT only addresses emotional needs, 47 out of 59 parents reported seeing improvements in other areas including behavioral, cognitive, linguistic, and social changes. All but one parent indicated that they would recommend MT to others. The survey results further revealed that even parents of children participating in MT had misconceptions regarding MT, which we describe in the paper. Parents reported inaccessibility and cost as other major limitations surrounding MT adoption. We conclude by discussing how technology solutions could mitigate issues with definition, distance, and cost, while maintaining the benefits of MT.

Plexlines: Tracking Socio-communicative Behaviors Using Timeline Visualizations.

In this paper, we visualize children's coordinated gaze, gesture, and vocalization to better understand communicative behaviors and to identify developmental delay, specifically in the domain of Autism Spectrum Disorders. To date, existing behavioral data from clinical assessment instruments are often stored in raw text files or spreadsheets. This wealth of data is then represented as a single number summarizing behavior. Our approach transforms this data into a graphical story of a child's behavior. To do this, we created Plexlines, a graphical record of a child's social and communicative behavior. When presented with Plexlines, clinicians and researchers formed their own strategies for exploring the visualizations and independently identified children in need of further evaluation. Feedback showed that Plexlines has the potential to be integrated into existing behavioral evaluation processes, aid in the detection of developmental delays in young children, and serve as a visual artifact to better communicate with parents.

Visualizing Syllables: Real-Time Computerized Feedback Within a Speech-Language Intervention.

Computerized technologies now offer unprecedented opportunities to provide real-time visual feedback to facilitate children's speech-language development. We employed a mixed-method design to examine the effectiveness of two speech-language interventions aimed at facilitating children's multisyllabic productions: one incorporated a novel computerized feedback system, VocSyl, while the other used a traditional noncomputerized pacing board. Eighteen children with a variety of diagnoses, all of whom were at the single word stage of development, enrolled in either one of the two explicit speech-language interventions (VocSyl or Pacing Board) or an active control group. Convergent findings between and within groups supported the effectiveness of the VocSyl condition. For the children with a clinical diagnosis of autism in particular, visual inspection of individual data on treatment versus control targets indicated positive treatment effects for both of the two children enrolled in the VocSyl condition and one of the two children enrolled in the Pacing Board condition. Although the study does not permit definitive conclusions about the effectiveness of any particular treatment tool or strategy in isolation, it offers preliminary support for the integration of real-time computerized feedback within speech-language intervention.