In this study, we summarized the current shooting trends of medical science popularization short videos, including host characteristics and commonly used shooting and production techniques, to enhance the understanding of medical scientific information dissemination on this emerging communication platform. Based on these non-medical factors, for the first time, we developed and validated five ML models for predicting the influence of these videos, achieving precise predictions prior to their release. More importantly, these models identified the significance of different influencing factors, providing guidance for the entire video production process. Therefore, this study will help improve public awareness of medical knowledge by elucidating how these factors interact and collectively affect the popularity and dissemination speed of medical content. By enhancing the popularity and dissemination likelihood of these videos, our study is expected to increase the impact of medical science popularization efforts, thereby contributing to the improvement of public health literacy.
It is necessary and meaningful to study the non-medical factors of medical education video through the TikTok. TikTok has become a vital video platform for sharing fascinating scientific knowledge[13]. More and more health care professionals use the TikTok to convey important health information to the public, and more research focuses on the analysis of medical care professional video content and form on TikTok[14–16]. Du et al[17] explored the content and quality of videos on the TikTok and Bilibili platforms, and analyzed the relationship with the number of views, comments, shares, and favorites. Rudisill et al[18] and wang et al[19] evaluated the reliability and educational quality of videos and found that longer video durations predicted higher scores, the former show that there is no independent correlation between the uploaded source or content and quality score, while the latter show that academic and clinical sources can lead to the higher video quality. A study noted the influence of non-medical factors such as video style, original music by analyzing the likes, comments, and reposts of the top 100 most popular micro-videos[16]. Li et al[20] investigate how the video attributes (video format, type and content) are related to quantitative indicators of user engagement (numbers of views, likes, comments and shares). Although these studies suggest that non-medical factors may be key to attracting the public to watch videos, there has few studies focused exclusively on these non-medical factors. Therefore, this study controlled for consistency in professionalism and quality to observe the impact of non-medical factors on the four influence indicators. The results further directly demonstrate the critical role of non-medical factors. The significant differences in views, likes, shares, and collections between videos caused by non-medical factors suggest that these factors may have a more decisive influence than the video's professionalism and quality. This can be primarily explained by the fact that the audience often lacks expertise in medical knowledge, making them likely to overlook medical professionalism and instead rely on non-medical factors to judge whether a science popularization video is worth watching and sharing.
From a methodological perspective, analyzing video health communication is currently widely based on content analysis methods[16, 21]. Some studies also use multivariate linear analysis based on traditional statistics to explore the factors related to video quality and associated factors[22, 23]. However, referring to the development of medical big data mining research, these methods have significant limitations in exploring the complex nonlinear relationships commonly present among data[24]. In recent times, ML has emerged as a cutting-edge technology for predictive modeling and decision-making, substantially enhancing the precision of outcome predictions[25]. Additionally, ML model can distinguish the importance of different variables, and avoid the one-sided and subjective observation of a single indicator alone[26]. Therefore, it has been widely applied in the development of predictive models across various research domains[27–29]. In the field of video science popularization, ML is commonly used to analyze and evaluate public willingness[30] and emotional tendencies[31, 32], as well as to analyze video quality[33, 34]. For example, by using ML to identify, retrieve, and qualify medical related and understandable YouTube videos, domain experts can then review and recommend these videos for dissemination and public education[35]. Usman et al[36] proposed that ML models can effectively predict customer satisfaction from healthcare datasets. Alghamdi et al[37] used ML models for fake news detection, which demonstrate good predictive performance. In this study, we adopted the application models of ML from the field of disease prediction to explore the development of influence prediction models for medical science popularization videos, by comparing the performance of 13 commonly used ML algorithms. Finally, the FR algorithm was confirmed as the best-performing model across the four outcome indicators, while the BNB algorithm showed consistent and satisfactory performance specifically for the “Comment” outcome. These findings regarding ML algorithms are consistent with patterns reported in numerous studies[38]. Our results not only indicate that non-medical factors can predict the influence of science popularization videos, but also demonstrate that ML algorithms can significantly enhance this predictive ability. Moreover, we found that nonlinear algorithms significantly outperform traditional linear algorithms (e.g., LR), further confirming the existence of complex data relationships between non-medical factors and outcomes.
We found that in terms of host characteristics, the chief physician and associate chief physician assume educational responsibilities, but the attending physician and resident physician are more popular among people. Although the chief physician and associate chief physician have more experience and expertise, lower-level physicians may be more humorous, their shooting methods or content being more vivid and interesting. Studies have shown that humor can significantly enhance user immersion and entertainment, especially when combined with medical information, thereby enhancing user acceptance[39, 40]. People are not very interested in the image of wearing a white coat, but they are more interested in medical personnel wearing surgical gowns. At the same time, research results show that people are more interested in and pay more attention to science popularization videos of surgical professionals. Moderate Body Language is not beneficial, more body language demonstrates good effects, which can demonstrate the professionalism and affinity of host. Surprisingly, make-up does not attract attention. Although people have requirements for beauty[41], this requirement seems to not applicable to medical science popularization.
In terms of Shooting techniques, the shooting location, scene, and angle have a higher weight. The video shooting in the department office is not good, while in the conference room is better. It may be because the environment of the department office is relatively noisy, the conference room is relatively quiet, resulting in better video shooting and presentation effects[42]. The dissemination effect of close-up shooting is better, and the shooting angles of the side and oblique sides are also better than those of frontal shooting. The video shoted in these methods are natural and clear, and therefore more popular among people. In terms of video production and publication, the length of video description, duration, and length of questions can all affect the dissemination and engagement. Videos on TikTok with the shortest duration received the most numbers of “likes", “comments", and “shares"[43]. Zhu et al[16] found that the presentation method of micro-video is more popular. The duration of the video should not be too long, and the title and video descriptions content should be concise, clear, and easy to understand[44]. Proper use of beauty filters is beneficial, but background music should be used with caution. Sometimes background music may give people a scripted feeling or mask some of the sound[45]. Medical videos should ensure their rigor and seriousness, and should be convincing and serious. Therefore, beauty filters should be used moderately, and appropriate background music should be chosen. The popularity and dissemination effect of videos released from 13:30 to 19:00 are better, videos released in the afternoon are more likely to be shared with others, and videos released later are more likely to receive likes. Most people are working or busy during the day, users are more likely to invest more effort for the time-consuming activity of watching the video in the evening.[46].
However, this study has certain limitations. Firstly, the videos screened in this study are in Chinese. Consequently, the findings derived from this study may not be readily applicable to videos in other languages found on TikTok. Secondly, we searched from January to March 2023 and obtained 286 samples only, which is relatively small, we will conduct larger sample studies in the future.