Purpose: The purpose of this study was to measure the level of physical activity during work and investigate its association with nonspecific low back pain.

Methods: 58 full-time female hospital ward nurses were included in the study. During the day shift, an activity meter was used to measure and record data, and after classifying activities into sitting, low-intensity physical activity, and mid- to high-intensity physical activity categories, the duration and intensity of each activity was calculated. In addition, the number and duration of breaks from work and interruptions in spells of sitting were also measured.

Results: A multiple regression analysis with the amount of change in low-back pain as the target variable and age, sitting patterns, mid- to high-intensity physical activity, and domain score as explanatory variables found significant differences in sitting patterns. Setting the amount of change in low-back pain as the target variable and age, total number of breaks from work, average length of spells of work and rest, and number of spells as the explanatory variables, multiple regression analysis found significant differences between the total number of breaks in work and rest.

Conclusion: Increases in lower back pain among ward nurses before and after their shifts was shown to be associated with sitting patterns. Inadequate breaks from work and spells of sitting could be a risk factor for developing and/or aggravating low back pain.

This study creates a model for estimating sentiment from tweets that include “work style reforms “.

The system to extract sentiment scores from the tweets was developed using MS Excel and VBA (Visual Basic for Applications). A total of 11,272 tweets were collected using Twitter's API v2 (Application Programming Interface v2), and 8,570 tweets were selected for analysis after removing retweets. The data was divided into training and test sets, and sentiment analysis was performed. The sentiment scores, labels, and tweet text obtained from the analysis were trained using a support vector machine (SVM). The performance of the test data was evaluated using a stratified 5-part cross-validation method.

The results are as follows: The sentiment analysis results for the training and test data indicated that 2,896 and 2,824 tweets were negative, respectively, while 1,389 and 1,461 were positive. The performance evaluation of the sentiment estimation model showed an area under the curve (AUC) of 0.936.

This study developed a system using Excel to extract sentiment scores and analyzed the sentimental words used in conjunction with “work style reforms”. The study developed an sentiment estimation model with a high classification performance of AUC 0.936 based on test data validation.