Developing Simplified Chinese Psychological Linguistic Analysis Dictionary for Microblog

Gao, Rui; Hao, Bibo; He, Li; Yusong, Gao; Zhu, Tingshao

doi:10.1007/978-3-319-02753-1_36

Cited by 143 publications

(112 citation statements)

References 22 publications

Supporting

Mentioning

108

Contrasting

Unclassified

Order By: Relevance

“…To describe the linguistic attributes, we leverage a psychological dictionary named "Language Inquiry and Word Count Dictionary" [20]. The simplified Chinese LIWC dictionary [21] is developed by Chinese psychologists and linguists, based on the psycholinguistic dictionary LIWC (http://www.liwc.net), which has been proved to be effective on determining affect in Twitter. It is composed of almost 4500 words and categorized into over 60 categories [20].…”

Section: ) Linguistic Attributesmentioning

confidence: 99%

User-level psychological stress detection from social media using deep neural network

Lin

Jia

Guo

et al. 2014

Proceedings of the 22nd ACM International Conference on Multimedia

138

115

View full text Add to dashboard Cite

It is of significant importance to detect and manage stress before it turns into severe problems. However, existing stress detection methods usually rely on psychological scales or physiological devices, making the detection complicated and costly. In this paper, we explore to automatically detect individuals' psychological stress via social media. Employing real online micro-blog data, we first investigate the correlations between users' stress and their tweeting content, social engagement and behavior patterns. Then we define two types of stress-related attributes: 1) low-level content attributes from a single tweet, including text, images and social interactions; 2) user-scope statistical attributes through their weekly micro-blog postings, leveraging information of tweeting time, tweeting types and linguistic styles. To combine content attributes with statistical attributes, we further design a convolutional neural network (CNN) with cross autoencoders to generate user-scope content attributes from low-level content attributes. Finally, we propose a deep neural network (DNN) model to incorporate the two types of userscope attributes to detect users' psychological stress. We test the trained model on four different datasets from major micro-blog platforms including Sina Weibo, Tencent Weibo and Twitter. Experimental results show that the proposed model is effective and efficient on detecting psychological stress from micro-blog data. We believe our model would be useful in developing stress detection tools for mental health agencies and individuals.

show abstract

Section: ) Linguistic Attributesmentioning

confidence: 99%

User-level psychological stress detection from social media using deep neural network

Lin

Jia

Guo

et al. 2014

Proceedings of the 22nd ACM International Conference on Multimedia

138

115

View full text Add to dashboard Cite

show abstract

“…The stress-category lexicon is built based on the "Simplified Chinese Language Inquiry and Word Count Dictionary" [9]. It contains 1307 words, which are categorized into four typical types, i.e., physiological, work-related, social and affection-related stress.…”

Section: ) Linguistic Attributesmentioning

confidence: 99%

Psychological stress detection from cross-media microblog data using Deep Sparse Neural Network

Lin

Jia

Guo

et al. 2014

2014 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

Long-term stress may lead to many severe physical and mental problems. Traditional psychological stress detection usually relies on the active individual participation, which makes the detection labor-consuming, time-costing and hysteretic. With the rapid development of social networks, people become more and more willing to share moods via microblog platforms. In this paper, we propose an automatic stress detection method from cross-media microblog data. We construct a three-level framework to formulate the problem. We first obtain a set of low-level features from the tweets. Then we define and extract middle-level representations based on psychological and art theories: linguistic attributes from tweets' texts, visual attributes from tweets' images, and social attributes from tweets' comments, retweets and favorites. Finally, a Deep Sparse Neural Network is designed to learn the stress categories incorporating the cross-media attributes. Experiment results show that the proposed method is effective and efficient on detecting psychological stress from microblog data.

show abstract

“…We crawled the 92 Weibo users' data through the Application Programming Interface (API) provided by Sina Weibo. After obtaining the online data of the users, we extracted the features of each user from two aspects: LIWC features (see Gao, Hao, Li, Gao, & Zhu, 2013;Zhao, Jiao, Bai, & Zhu, 2016, for more details) and behavioral features.…”

Section: Measurementmentioning

confidence: 99%

Using social media to explore the linguistic features in female adults with childhood sexual abuse by Linguistic Inquiry and Word Count

Wan

Sun

Liu

et al. 2019

Human Behav and Emerg Tech

View full text Add to dashboard Cite

The adverse impact of childhood sexual abuse experience on a person's physical and mental health is long‐lasting. The disadvantageous influence can be reflected in the language expression even if they grow up, especially when the language is not monitored intentionally by the speaker. However, few researchers have focused on the language expression characteristics of this group. This study aims to analyze the message of social media to explore the difference of language expression between adult females with childhood sexual abuse experience (CSA group) and adult women without such experience (control group) by Linguistic Inquiry and Word Count (LIWC). We collected 46 victims (all females) and 46 nonvictims (gender‐matched with CSA group) on Sina Weibo, and we applied LIWC to encode and count all the text messages posted on the social platforms. The results of this research suggested that the CSA group differed from the control group in multiple indicators, especially in psychological process words. The victims were less likely to refer to psychological process words, such as body words, sex words, etc. than the nonvictims, however, they preferred to mention human words. Moreover, compared to the control group, the CSA group had published fewer contents and used fewer words that represent the present tense in the social media platforms. The present study provides the research basis for identifying the CSA group in social media platforms in the future.

show abstract

Developing Simplified Chinese Psychological Linguistic Analysis Dictionary for Microblog

Cited by 143 publications

References 22 publications

User-level psychological stress detection from social media using deep neural network

User-level psychological stress detection from social media using deep neural network

Psychological stress detection from cross-media microblog data using Deep Sparse Neural Network

Using social media to explore the linguistic features in female adults with childhood sexual abuse by Linguistic Inquiry and Word Count

Contact Info

Product

Resources

About