開始時刻
前のセッションの直後
この勉強会は終了しました。ご参加ありがとうございました。
The need to generate convincing simulation of voices often arises in the context of avatar therapy, a treatment approach for disorders such as schizophrenia. This treatment involves patients interacting with simulations of the entity they imagine to be responsible for the voices they hear, for which there is often no external reference available. However, in such scenarios, there is little knowledge of how to design and reproduce these voices in a convincing manner.
Existing voice manipulation interfaces are often complex to use, and highly limited in their ability to modify vocal characteristics beyond small adjustments.
To address these challenges, we designed a framework that allows users to explore and select from a large set of voices, and thereafter manipulate the voice(s) to converge towards an effective match for one they have in mind. We demonstrated both the usability and superior performance of this system compared to existing voice manipulation interfaces.
Various automated eating detection wearables have been proposed to monitor food intakes. While these systems overcome the forgetfulness of manual user journaling, they typically show low accuracy at outside-the-lab environments or have intrusive form-factors (e.g., headgear). Eyeglasses are emerging as a socially-acceptable eating detection wearable, but existing approaches require custom-built frames and consume large power. We propose MyDJ, an eating detection system that could be attached to any eyeglass frame. MyDJ achieves accurate and energy-efficient eating detection by capturing complementary chewing signals on a piezoelectric sensor and an accelerometer. We evaluated the accuracy and wearability of MyDJ with 30 subjects in uncontrolled environments, where six subjects attached MyDJ on their own eyeglasses for a week. Our study shows that MyDJ achieves 0.919 F1-score in eating episode coverage, with 4.03× battery time over the state-of-the-art systems. In addition, participants reported wearing MyDJ was almost as comfortable (94.95%) as wearing regular eyeglasses.
Data Videos (DVs), or animated infographics that tell stories with data, are becoming increasingly popular. Despite their potential to induce attitude change, little is explored about how to produce effective DVs. This paper describes two studies that explored factors linked to the potential of health DVs to improve viewers' behavioural change intentions. We investigated: 1) how viewers' affect is linked to their behavioural change intentions; 2) how these affect are linked to the viewers' personality traits; 3) which attributes of DVs are linked to their persuasive potential. Results from both studies indicated that viewers' negative affect lowered their behavioural change intentions. Individuals with higher neuroticism exhibited higher negative affect and were harder to convince. Finally, Study 2 proved that providing any solutions to the health problem, presented in the DV, made the viewers perceive the videos as more actionable while lowering their negative affect, and importantly, induced higher behavioural change intentions.
Individuals and communities around the world are increasingly exposed to extreme heat as a result of climate change. Urban residents are particularly vulnerable to extreme heat due to the urban heat island effect. However, understanding an individual's heat exposure and risk is difficult to assess due to variations in temperature within an urban environment. In this paper, we examine the potential for wearable temperature sensors to accurately measure personal heat exposure. We synthesize literature from fields spanning urban planning to public health and present the results of a user study validating a set of four commonly used off-the-shelf temperature sensors in two different urban settings across five on-body locations. Our investigation found that wearable temperature sensors are less reliable in highly urban areas and when worn in direct sunlight. We discuss important design considerations for wearable temperature sensors and identify actionable ways to improve future studies.
Image-based sexual abuse (IBSA) is a severe social problem that causes survivors tremendous pain. IBSA survivors may encounter a lack of information and victim blame when seeking online and offline assistance. While institutions support survivors, they cannot be available 24 hours a day. Because the immediate reaction to IBSA is crucial to remove intimate images and prevent further distribution, survivors need first responders who are always accessible and do not blame them. Chatbots are constantly available, do not judge the conversation partner, and may deliver structured information and words of comfort. Therefore, we developed a chatbot to provide information and emotional support to IBSA survivors in dealing with their abuse. We analyzed nine chatbots for sexual violence survivors to identify common design elements. In addition, we sought advice from five professional counselors about the challenges survivors have while responding to their harm. We conducted a user study with 25 participants to determine the chatbot's effectiveness in providing information and emotional support compared to internet search. The chatbot was better than the internet search regarding information organization, accessibility, and conciseness. Furthermore, the chatbot excels in providing emotional support to survivors. We discuss the survivor-centered information structure and design consideration of emotionally supportive conversation.