A textual and visual features-jointly driven hybrid intelligent system for digital physical education teaching quality evaluation.

The utilization of intelligent computing in digital teaching quality evaluation has been a practical demand in smart cities. Currently, related research works can be categorized into two types: textual data-based approaches and visual data-based approaches. Due to the gap between their different formats and modalities, it remains very challenging to integrate them together when conducting digital teaching quality evaluation. In fact, the two types of information can both reflect distinguished knowledge from their own perspectives. To bridge this gap, this paper proposes a textual and visual features-jointly driven hybrid intelligent system for digital teaching quality evaluation. Visual features are extracted with the use of a multiscale convolution neural network by introducing receptive fields with different sizes. Textual features serve as the auxiliary contents for major visual features, and are extracted using a recurrent neural network. At last, we implement the proposed method through some simulation experiments to evaluate its practical running performance, and a real-world dataset collected from teaching activities is employed for this purpose. We obtain some groups of experimental results, which reveal that the hybrid intelligent system developed by this paper can bring more than 10% improvement of efficiency towards digital teaching quality evaluation.

Detecting subtle signs of depression with automated speech analysis in a non-clinical sample.

BACKGROUND: Automated speech analysis has gained increasing attention to help diagnosing depression. Most previous studies, however, focused on comparing speech in patients with major depressive disorder to that in healthy volunteers. An alternative may be to associate speech with depressive symptoms in a non-clinical sample as this may help to find early and sensitive markers in those at risk of depression. METHODS: We included n = 118 healthy young adults (mean age: 23.5 ± 3.7 years; 77% women) and asked them to talk about a positive and a negative event in their life. Then, we assessed the level of depressive symptoms with a self-report questionnaire, with scores ranging from 0-60. We transcribed speech data and extracted acoustic as well as linguistic features. Then, we tested whether individuals below or above the cut-off of clinically relevant depressive symptoms differed in speech features. Next, we predicted whether someone would be below or above that cut-off as well as the individual scores on the depression questionnaire. Since depression is associated with cognitive slowing or attentional deficits, we finally correlated depression scores with performance in the Trail Making Test. RESULTS: In our sample, n = 93 individuals scored below and n = 25 scored above cut-off for clinically relevant depressive symptoms. Most speech features did not differ significantly between both groups, but individuals above cut-off spoke more than those below that cut-off in the positive and the negative story. In addition, higher depression scores in that group were associated with slower completion time of the Trail Making Test. We were able to predict with 93% accuracy who would be below or above cut-off. In addition, we were able to predict the individual depression scores with low mean absolute error (3.90), with best performance achieved by a support vector machine. CONCLUSIONS: Our results indicate that even in a sample without a clinical diagnosis of depression, changes in speech relate to higher depression scores. This should be investigated in more detail in the future. In a longitudinal study, it may be tested whether speech features found in our study represent early and sensitive markers for subsequent depression in individuals at risk.

Textual Features and Risk Preference Effects on Mental Health Education Among Teenager Students in Chongqing, China.

Background: Mental health is a public health problem of great concern. Previous studies show that textual features and individual psychological characteristics can influence the effect of receiving information. Purpose: This study explores whether textual features influence the persuasiveness of teenager students' mental health education while considering the influence of risk preference. Methods: From November to December 2021, a cross-sectional study was conducted among 1,869 teenager students in grade 7-12 in Chongqing, China. Wilcoxon signed-rank test, multiple logistic regression, and subgroup analysis were used to analyze the data. Results: Among the four textual features mentioned in this study, a significant difference was reported in the persuasive effects of information with and without numerical features (p < 0.001), and such information tended to include digital features. The result for the symbolic features (p < 0.001) was consistent with the numerical features. The persuasive effects of positive and negative emotional information significantly differed (p < 0.001), with the former showing a better performance. No significant differences were observed between the persuasive effects of information with and without emotional conflicts (p > 0.05). Combined with those from the risk preference analysis, results showed that the regulatory effect of risk preference was only reflected in emotional conflicts. Students who prefer having no emotional conflict in the text showed the characteristics of risk avoidance, or lower grades, or rural or school accommodation. Most teenager students are also risk averse, especially females (or = 2.223, 95%CI:1.755-2.815) and juniors (or = 1.533, 95%CI: 1.198-1.963). Conclusion: The numbers, symbols, and positive emotions in the text generate an active effect on teenager students receiving mental health education. Students avoiding risk are inclined to read texts without emotional conflicts. The probability of male choosing texts with positive emotional polarity is 33.5% lower than that of female. Female students and those from lower grades also demonstrate a higher inclination to risk avoidance compared with their male and higher grade counterparts. Therefore, educational materials with different text characteristics should be developed for teenager students with varying characteristics.

Effect of Textual Features on the Success of Medical Crowdfunding: Model Development and Econometric Analysis from the Tencent Charity Platform.

BACKGROUND: Medical crowdfunding utilizes the internet to raise medical funds. Medical crowdfunding has developed rapidly worldwide; however, most medical crowdfunding projects fail to raise the targeted funds. Therefore, a very important research problem that has not received sufficient attention from the existing literature is identifying which factors affect the success of medical crowdfunding projects. OBJECTIVE: The aim of this study was to examine the effect of textual features of medical crowdfunding projects on their success rate using 4903 real projects from the Tencent Charity platform, a well-known medical crowdfunding platform in China. In particular, according to Aristotle's theory of persuasion, we divided the project text of medical crowdfunding into the project title and project details, which were analyzed from two perspectives (existence and extent) to explore their respective impacts. METHODS: We established a research framework to meet our research goals. The process was divided into five main parts. We first collected data from Tencent Charity using Python programs and cleaned the datasets. Second, we selected variables and built the research model based on previous studies and the theory of persuasion. Next, the selected variables were extracted from the project text. We then performed econometric analysis using multiple regression analysis. Finally, we evaluated the results of econometric analysis to extract knowledge. RESULTS: In the project title, the presence of the patient's disease (P=.04) and occupation (P=.01) had a positive impact on the success rate of fundraising, whereas the presence of age (P<.001), gender (P=.001), and negative emotions (P=.04) had a negative impact. In the project details, the presence of the patient's occupation (P=.01), monetary evidence (P=.02), and negative emotions (P=.04) played a positive role in the fundraising success rate, whereas the presence of age (P<.001) and positive emotions (P<.001) played a negative role. Moreover, in the project details, high-frequency monetary evidence (P=.02) and negative words (P=.02), as well as a short narrative length (P=.01) were conducive to succeeding in medical crowdfunding. Younger patients were more likely to obtain a higher success rate in medical crowdfunding. For patients whose occupations were national civil servant, professional skill worker, clerk, business and service worker, solider, child, student, and public-spirited person, the success rate of fundraising decreased sequentially. CONCLUSIONS: This study collected 4903 valid data from Tencent Charity, and identified which factors in the project text play an important role in the success rate of medical crowdfunding from the perspective of existence and extent. We found that in addition to the project details, the features of the project title also have an important impact on the success rate of fundraising. These findings provide important theoretical and managerial implications for medical crowdfunding.