ABSTRACT
BACKGROUND: This study focuses on health-related content (HRC) on YouTube and addresses the issue of misinformation on this platform. While previous research centered on content evaluations by experts, this study takes a user-centered approach and aims to explore users' experiences with and perceptions of HRC videos and to establish links between these perceptions and some socio-demographic characteristics including age, gender, profession, and educational level. METHODS: A quantitative research design was used in the study. 3,000 YouTube users responded to a 35-item anonymous questionnaire to collect information about the content they watch toward decision-making, their perceptions of the usefulness and bias of this content, what they identify as quality indicators for HRC, and what they recommend to improve the quality of such content on YouTube. The data were analyzed using descriptive statistics, frequency, and correlation analyses. RESULTS: The results reveal that 87.6 percent (n=2630) of the participants watch HRC on YouTube, and 84.7 percent (n=2542) make decisions based on what they watch. Exercise and bodybuilding videos are the most popular, with over half of the participants watching them. 40 percent of the users watch YouTube videos to decide whether to consult a doctor or adopt specific health-related practices. In contrast to evaluations by experts in previous studies, most respondents perceive HRC videos on YouTube as useful and do not find connections between video quality and surface features like the number of views and likes. Weak or no correlations were observed between the perceived usefulness of HRC videos and age, gender, profession, or educational level. Participants' recommendations for enhancing HRC quality align with previous research findings. CONCLUSIONS: Users turn to YouTube not only for health information but also as a decision-making tool. Combined with their generally positive attitudes towards content quality on this platform, this can have significant consequences for their health. Follow-up studies are needed to get more insights into decision-making behaviors and how users assess their decisions in retrospect.
Subject(s)
Social Media , Humans , Bias , Communication , Surveys and Questionnaires , Video Recording , Decision MakingABSTRACT
Drone-person tracking in uniform appearance crowds poses unique challenges due to the difficulty in distinguishing individuals with similar attire and multi-scale variations. To address this issue and facilitate the development of effective tracking algorithms, we present a novel dataset named D-PTUAC (Drone-Person Tracking in Uniform Appearance Crowd). The dataset comprises 138 sequences comprising over 121 K frames, each manually annotated with bounding boxes and attributes. During dataset creation, we carefully consider 18 challenging attributes encompassing a wide range of viewpoints and scene complexities. These attributes are annotated to facilitate the analysis of performance based on specific attributes. Extensive experiments are conducted using 44 state-of-the-art (SOTA) trackers, and the performance gap between the visual object trackers on existing benchmarks compared to our proposed dataset demonstrate the need for a dedicated end-to-end aerial visual object tracker that accounts the inherent properties of aerial environment.
ABSTRACT
BACKGROUND: YouTube is a valuable source of health-related educational material which can have a profound impact on people's behaviors and decisions. However, YouTube contains a wide variety of unverified content that may promote unhealthy behaviors and activities. We aim in this systematic review to provide insight into the published literature concerning the quality of health information and educational videos found on YouTube. METHODS: We searched Google Scholar, Medline (through PubMed), EMBASE, Scopus, Direct Science, Web of Science, and ProQuest databases to find all papers on the analysis of medical and health-related content published in English up to August 2020. Based on eligibility criteria, 202 papers were included in our study. We reviewed every article and extracted relevant data such as the number of videos and assessors, the number and type of quality categories, and the recommendations made by the authors. The extracted data from the papers were aggregated using different methods to compile the results. RESULTS: The total number of videos assessed in the selected articles is 22,300 (median = 94, interquartile range = 50.5-133). The videos were evaluated by one or multiple assessors (median = 2, interquartile range = 1-3). The video quality was assessed by scoring, categorization, or based on creators' bias. Researchers commonly employed scoring systems that are either standardized (e.g., GQS, DISCERN, and JAMA) or based upon the guidelines and recommendations of professional associations. Results from the aggregation of scoring or categorization data indicate that health-related content on YouTube is of average to below-average quality. The compiled results from bias-based classification show that only 32% of the videos appear neutral toward the health content. Furthermore, the majority of the studies confirmed either negative or no correlation between the quality and popularity of the assessed videos. CONCLUSIONS: YouTube is not a reliable source of medical and health-related information. YouTube's popularity-driven metrics such as the number of views and likes should not be considered quality indicators. YouTube should improve its ranking and recommender system to promote higher-quality content. One way is to consider expert reviews of medical and health-related videos and to include their assessment data in the ranking algorithm.
