• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.9
• /
• pp.381-390
• /
• 2022

Influenced by a culture that prefers non-face-to-face activity during the COVID-19 pandemic, chatbot usage is accelerating. Chatbots have been used for various purposes, not only for customer service in businesses and social conversations for fun but also for mental health. Chatbots are a platform where users can easily talk about their depressed moods because anonymity is guaranteed. However, most relevant research has been on social media data, especially Twitter data, and few studies have analyzed the commercially used chatbots data. In this study, we identified the characteristics of depressive discourse in user-chatbot interaction data by analyzing the chats, including the word 'depress,' using the topic modeling algorithm and the text-mining technique. Moreover, we compared its characteristics with those of the depressive moods in the Twitter data. Finally, we draw several design guidelines and suggest avenues for future research based on the study findings.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.43 no.5
• /
• pp.772-783
• /
• 2014

This study aimed to investigate the relationships between depressed mood and life style patterns, including smoking, alcohol drinking, and physical inactivity in Koreans aged 40 years, which is a critical life transition period. Based on the Life Transition Period Health Examination at the Korea Association of Health Promotion conducted in 2011 (n=27,684), participants were categorized into a depressed mood group and a non-depressed mood group based on the results of the Primary Mental Health Questionnaire. The depressed mood group showed higher tendency for smoking compared to the non-depressed mood group. Current and ex-smokers were about twice as likely to have a depressed mood as the non-smokers. The prevalence of nicotine dependency was significantly higher in the depressed mood group. The number of days and amount of alcohol consumption were significantly correlated with depressed mood. The prevalence of alcohol dependence and alcohol abuse was higher in the depressed mood group than in the non-depressed mood group. The frequency of high-intensity exercise per week was negatively correlated with the number of people with a depressed mood. This study showed the significant relationships between depressed mood and smoking, alcohol drinking, and physical activity in adults during an important life transition period. This implies that the development of proper lifestyle intervention or education may be needed to prevent depressed moods in this age group.

• Korean Journal of Child Studies
• /
• v.33 no.6
• /
• pp.149-168
• /
• 2012

This study explored the effects of maternal ambivalence over emotional expressiveness (AEE) and mother-adolescent communication on adolescent depression (depressed affect, positive affect, somatic symptoms and activity inhibition, interpersonal difficulties). Data were taken from 233 middle school students (128 boys, 105 girls) and their mothers. Regression analyses showed varying gender differences in the relationships among these variables. Boys with high maternal AEE had lower positive affect, and higher depressive affect, somatic symptoms and activity inhibition, and interpersonal difficulties, whereas girls' moods were not influenced by maternal AEE. In addition, boys with problems in mother-dolescent communication exhibited lower positive affect, higher depressed affect and interpersonal difficulties, but open communication was not related to any depressive symptoms. The mother-adolescent communication type did not appear to be associated with depression in girls either. Both boys and girls both had less open communication and more problem communication with mothers experiencing high AEE. Problem communication with mothers partially mediated the relationship between maternal AEE and interpersonal difficulties in boys only. Examination of maternal ambivalence over emotional expressiveness provides a deeper context for our understanding of negative family communication patterns and the psychological consequences, especially in mother-adolescent boy dyads.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1626-1638
• /
• 2019

Social Networking Sites (SNS) provide people with unique online social interaction environments where users can disclose their thoughts, feelings, and opinions to their personal contacts. Although previous studies have suggested that such activities produce positive effects on SNS user well-being, this study considered potential negative effects by investigating the relationship between SNS use and depression. In particular, This stydy examined how specific activities are related to different types of social comparison (upward/downward/horizontal) and how these different types of social comparison influence depressed moods among college students. The analysis of a survey of 245 Instagram users found that (1) looking at other people's status updates and commenting on other people's photos influences upward social comparison, (2) frequency of Instagram use predicts upward/downward/horizontal social comparison, and (3) upward social comparison was postively associated with depression, while downward social comparison was negatively associated with depression. Furthermore, the path anlaysis show that social comparison mediates the effect of Instagram use on depression. It suggests that Instagram use does not directly increase depression but it can lead to depression when social comparison on Instagram triggers depression.

• Journal of the Korea Convergence Society
• /
• v.9 no.1
• /
• pp.419-431
• /
• 2018

In this paper, we propose a novel method for monitoring mood trend of Twitter users by analyzing their daily tweets for a long period. Then, to more accurately understand their tweets, we analyze all types of content in tweets, i.e., texts and emoticons, and images, thus develop a multimodal sentiment analysis method. In the proposed method, two single-modal analyses first are performed to extract the users' moods hidden in texts and images: a lexicon-based and learning-based text classifier and a learning-based image classifier. Thereafter, the extracted moods from the respective analyses are combined into a tweet mood and aggregated a daily mood. As a result, the proposed method generates a user daily mood flow graph, which allows us for monitoring the mood trend of users more intuitively. For evaluation, we perform two sets of experiment. First, we collect the data sets of 40,447 data. We evaluate our method via comparing the state-of-the-art techniques. In our experiments, we demonstrate that the proposed multimodal analysis method outperforms other baselines and our own methods using text-based tweets or images only. Furthermore, to evaluate the potential of the proposed method in monitoring users' mood trend, we tested the proposed method with 40 depressive users and 40 normal users. It proves that the proposed method can be effectively used in finding depressed users.