Abstract-One of the key challenges for users of social media is judging the topical expertise of other users in order to select trustful information sources about specific topics and to judge credibility of content produced by others. In this paper, we explore the usefulness of different types of user-related data for making sense about the topical expertise of Twitter users. Types of user-related data include messages a user authored or re-published, biographical information a user published on his/her profile page and information about user lists to which a user belongs. We conducted a user study that explores how useful different types of data are for informing human's expertise judgements. We then used topic modeling based on different types of data to build and assess computational expertise models of Twitter users. We use Wefollow directories as a proxy measurement for perceived expertise in this assessment.Our findings show that different types of user-related data indeed differ substantially in their ability to inform computational expertise models and humans's expertise judgements. Tweets and retweets -which are often used in literature for gauging the expertise area of users -are surprisingly useless for inferring the expertise topics of their authors and are outperformed by other types of user-related data such as information about users' list memberships. Our results have implications for algorithms, user interfaces and methods that focus on capturing expertise of social media users.

Patients with type II diabetes often struggle with self-care, including adhering to complex medication regimens and managing their blood glucose levels. Medication nonadherence in this population reflects many factors, including a gap between the demands of taking medication and the limited literacy and cognitive resources that many patients bring to this task. This gap is exacerbated by a lack of health system support, such as inadequate patient-provider collaboration. The goal of our project is to improve self-management of medications and related health outcomes by providing system support. The Medtable™ is an Electronic Medical Record (EMR)-integrated tool designed to support patient-provider collaboration needed for medication management. It helps providers and patients work together to create effective medication schedules that are easy to implement. We describe the development and initial evaluation of the tool, as well as the process of integrating it with an EMR system in general internal medicine clinics. A planned evaluation study will investigate whether an intervention centered on the Medtable™ improves medication knowledge, adherence, and health outcomes relative to a usual care control condition among type II diabetic patients struggling to manage multiple medications.

Analyzing usability test videos is arduous. Although recent research showed the promise of AI in assisting with such tasks, it remains largely unknown how AI should be designed to facilitate effective collaboration between user experience (UX) evaluators and AI. Inspired by the concepts of agency and work context in human and AI collaboration literature, we studied two corresponding design factors for AI-assisted UX evaluation: explanations and synchronization. Explanations allow AI to further inform humans how it identifies UX problems from a usability test session; synchronization refers to the two ways humans and AI collaborate: synchronously and asynchronously. We iteratively designed a tool-AI Assistant-with four versions of UIs corresponding to the two levels of explanations (with/without) and synchronization (sync/async). By adopting a hybrid wizard-of-oz approach to simulating an AI with reasonable performance, we conducted a mixed-method study with 24 UX evaluators identifying UX problems from usability test videos using AI Assistant. Our quantitative and qualitative results show that AI with explanations, regardless of being presented synchronously or asynchronously, provided better support for UX evaluators' analysis and was perceived more positively; when without explanations, synchronous AI better improved UX evaluators' performance and engagement compared to the asynchronous AI. Lastly, we present the design implications for AI-assisted UX evaluation and facilitating more effective human-AI collaboration.

Comparative Effectiveness Research (CER) is defined as the generation and synthesis of evidence that compares the benefits and harms of different prevention and treatment methods. This is becoming an important field in informing health care providers about the best treatment for individual patients. Currently, the two major approaches in conducting CER are observational studies and randomized clinical trials. These approaches, however, often suffer from either scalability or cost issues.In this paper, we propose a third approach of conducting CER by utilizing online personal health messages, e.g., comments on online medical forums. The approach is effective in resolving the scalability and cost issues, enabling rapid deployment of system to identify treatments of interests, and developing hypotheses for formal CER studies. Moreover, by utilizing the demographic information of the patients, this approach may provide valuable results on the preferences of different demographic groups. Demographic information is extracted using our high precision automated demographic extraction algorithm. This approach is capable of extracting more than 30% of users' age and gender information.We conducted CER by utilizing personal health messages on breast cancer and heart disease. We were able to generate statiatically valid results, many of which have already been validated by clinical trials. Others could become hypothesis to be tested in future CER research.

No abstract