Tingshao Zhu

Developing Simplified Chinese Psychological Linguistic Analysis Dictionary for Microblog

The words that people use could reveal their emotional states, intentions, thinking styles, individual differences, etc. LIWC (Linguistic Inquiry and Word Count) has been widely used for psychological text analysis, and its dictionary is the core. The Traditional Chinese version of LIWC dictionary has been released, which is a translation of LIWC English dictionary. However, Simplified Chinese which is the worlds most widely used language has subtle differences with Traditional Chinese. Furthermore, both English LIWC dictionary and Traditional Chinese version dictionary were both developed for relatively formal text. Microblog has become more and more popular in China nowadays. Original LIWC dictionaries take less consideration on microblog popular words, which makes it less applicable for text analysis on microblog. In this study, a Simplified Chinese LIWC dictionary is established according to LIWC categories. After translating Traditional Chinese dictionary into Simplified Chinese, five thousand words most frequently used in microblog are added into the dictionary. Four graduate students of psychology rated whether each word belonged in a category. The reliability and validity of Simplified Chinese LIWC dictionary were tested by these four judges. This new dictionary could contribute to all the text analysis on microblog in future.

Predicting Big Five Personality Traits of Microblog Users

Personality can be defined as a set of characteristics which makes a person unique. The study of personality is of central importance in psychology. Conventional personality assessment is performed by self-report inventory, which costs much manual efforts and cannot be done in real time. To solve these problems, this research aims to measure the Big-Five personality from the usages of Sina Microblog objectively. By conducting a user study with 444 users, this paper proposes multi-task regression and incremental regression algorithms to predict the Big-Five personality from online behaviors. The results indicate that personality can be predicted with a high accuracy through online Microblog usage.

Web communities identification from random walks

We propose a technique for identifying latent Web communities based solely on the hyperlink structure of the WWW, via random walks. Although the topology of the Directed Web Graph encodes important information about the content of individual Web pages, it also reveals useful meta-level information about user communities. Random walk models are capable of propagating local link information throughout the Web Graph, which can be used to reveal hidden global relationships between different regions of the graph. Variations of these random walk models are shown to be effective at identifying latent Web communities and revealing link topology. To efficiently extract these communities from the stationary distribution defined by a random walk, we exploit a computationally efficient form of directed spectral clustering. The performance of our approach is evaluated in real Web applications, where the method is shown to effectively identify latent Web communities based on link topology only.

Identifying Chinese Microblog Users With High Suicide Probability Using Internet-Based Profile and Linguistic Features: Classification Model

Background Traditional offline assessment of suicide probability is time consuming and difficult in convincing at-risk individuals to participate. Identifying individuals with high suicide probability through online social media has an advantage in its efficiency and potential to reach out to hidden individuals, yet little research has been focused on this specific field. Objective The objective of this study was to apply two classification models, Simple Logistic Regression (SLR) and Random Forest (RF), to examine the feasibility and effectiveness of identifying high suicide possibility microblog users in China through profile and linguistic features extracted from Internet-based data. Methods There were nine hundred and nine Chinese microblog users that completed an Internet survey, and those scoring one SD above the mean of the total Suicide Probability Scale (SPS) score, as well as one SD above the mean in each of the four subscale scores in the participant sample were labeled as high-risk individuals, respectively. Profile and linguistic features were fed into two machine learning algorithms (SLR and RF) to train the model that aims to identify high-risk individuals in general suicide probability and in its four dimensions. Models were trained and then tested by 5-fold cross validation; in which both training set and test set were generated under the stratified random sampling rule from the whole sample. There were three classic performance metrics (Precision, Recall, F1 measure) and a specifically defined metric “Screening Efficiency” that were adopted to evaluate model effectiveness. Results Classification performance was generally matched between SLR and RF. Given the best performance of the classification models, we were able to retrieve over 70% of the labeled high-risk individuals in overall suicide probability as well as in the four dimensions. Screening Efficiency of most models varied from 1/4 to 1/2. Precision of the models was generally below 30%. Conclusions Individuals in China with high suicide probability are recognizable by profile and text-based information from microblogs. Although there is still much space to improve the performance of classification models in the future, this study may shed light on preliminary screening of risky individuals via machine learning algorithms, which can work side-by-side with expert scrutiny to increase efficiency in large-scale-surveillance of suicide probability from online social media.

Using Linguistic Features to Estimate Suicide Probability of Chinese Microblog Users

If people with high risk of suicide can be identified through social media like microblog, it is possible to implement an active intervention system to save their lives. Based on this motivation, the current study administered the Suicide Probability Scale(SPS) to 1041 weibo users at Sina Weibo, which is a leading microblog service provider in China. Two NLP (Natural Language Processing) methods, the Chinese edition of Linguistic Inquiry and Word Count (LIWC) lexicon and Latent Dirichlet Allocation (LDA), are used to extract linguistic features from the Sina Weibo data. We trained predicting models by machine learning algorithm based on these two types of features, to estimate suicide probability based on linguistic features. The experiment results indicate that LDA can find topics that relate to suicide probability, and improve the performance of prediction. Our study adds value in prediction of suicidal probability of social network users with their behaviors.

Assessing Suicide Risk and Emotional Distress in Chinese Social Media: A Text Mining and Machine Learning Study

Background Early identification and intervention are imperative for suicide prevention. However, at-risk people often neither seek help nor take professional assessment. A tool to automatically assess their risk levels in natural settings can increase the opportunity for early intervention. Objective The aim of this study was to explore whether computerized language analysis methods can be utilized to assess one’s suicide risk and emotional distress in Chinese social media. Methods A Web-based survey of Chinese social media (ie, Weibo) users was conducted to measure their suicide risk factors including suicide probability, Weibo suicide communication (WSC), depression, anxiety, and stress levels. Participants’ Weibo posts published in the public domain were also downloaded with their consent. The Weibo posts were parsed and fitted into Simplified Chinese-Linguistic Inquiry and Word Count (SC-LIWC) categories. The associations between SC-LIWC features and the 5 suicide risk factors were examined by logistic regression. Furthermore, the support vector machine (SVM) model was applied based on the language features to automatically classify whether a Weibo user exhibited any of the 5 risk factors. Results A total of 974 Weibo users participated in the survey. Those with high suicide probability were marked by a higher usage of pronoun (odds ratio, OR=1.18, P=.001), prepend words (OR=1.49, P=.02), multifunction words (OR=1.12, P=.04), a lower usage of verb (OR=0.78, P<.001), and a greater total word count (OR=1.007, P=.008). Second-person plural was positively associated with severe depression (OR=8.36, P=.01) and stress (OR=11, P=.005), whereas work-related words were negatively associated with WSC (OR=0.71, P=.008), severe depression (OR=0.56, P=.005), and anxiety (OR=0.77, P=.02). Inconsistently, third-person plural was found to be negatively associated with WSC (OR=0.02, P=.047) but positively with severe stress (OR=41.3, P=.04). Achievement-related words were positively associated with depression (OR=1.68, P=.003), whereas health- (OR=2.36, P=.004) and death-related (OR=2.60, P=.01) words positively associated with stress. The machine classifiers did not achieve satisfying performance in the full sample set but could classify high suicide probability (area under the curve, AUC=0.61, P=.04) and severe anxiety (AUC=0.75, P<.001) among those who have exhibited WSC. Conclusions SC-LIWC is useful to examine language markers of suicide risk and emotional distress in Chinese social media and can identify characteristics different from previous findings in the English literature. Some findings are leading to new hypotheses for future verification. Machine classifiers based on SC-LIWC features are promising but still require further optimization for application in real life.

Sensing Subjective Well-being from Social Media

Subjective Well-being(SWB), which refers to how people experience the quality of their lives, is of great use to public policy-makers as well as economic, sociological research, etc. Traditionally, the measurement of SWB relies on time-consuming and costly self-report questionnaires. Nowadays, people are motivated to share their experiences and feelings on social media, so we propose to sense SWB from the vast user generated data on social media. By utilizing 1785 users’ social media data with SWB labels, we train machine learning models that are able to “sense” individual SWB. Our model, which attains the state-of-the-art prediction accuracy, can then be applied to identify large amount of social media users’ SWB in time with low cost.

Creating a Chinese suicide dictionary for identifying suicide risk on social media

Introduction. Suicide has become a serious worldwide epidemic. Early detection of individual suicide risk in population is important for reducing suicide rates. Traditional methods are ineffective in identifying suicide risk in time, suggesting a need for novel techniques. This paper proposes to detect suicide risk on social media using a Chinese suicide dictionary. Methods. To build the Chinese suicide dictionary, eight researchers were recruited to select initial words from 4,653 posts published on Sina Weibo (the largest social media service provider in China) and two Chinese sentiment dictionaries (HowNet and NTUSD). Then, another three researchers were recruited to filter out irrelevant words. Finally, remaining words were further expanded using a corpus-based method. After building the Chinese suicide dictionary, we tested its performance in identifying suicide risk on Weibo. First, we made a comparison of the performance in both detecting suicidal expression in Weibo posts and evaluating individual levels of suicide risk between the dictionary-based identifications and the expert ratings. Second, to differentiate between individuals with high and non-high scores on self-rating measure of suicide risk (Suicidal Possibility Scale, SPS), we built Support Vector Machines (SVM) models on the Chinese suicide dictionary and the Simplified Chinese Linguistic Inquiry and Word Count (SCLIWC) program, respectively. After that, we made a comparison of the classification performance between two types of SVM models. Results and Discussion. Dictionary-based identifications were significantly correlated with expert ratings in terms of both detecting suicidal expression (r = 0.507) and evaluating individual suicide risk (r = 0.455). For the differentiation between individuals with high and non-high scores on SPS, the Chinese suicide dictionary (t1: F1 = 0.48; t2: F1 = 0.56) produced a more accurate identification than SCLIWC (t1: F1 = 0.41; t2: F1 = 0.48) on different observation windows. Conclusions. This paper confirms that, using social media, it is possible to implement real-time monitoring individual suicide risk in population. Results of this study may be useful to improve Chinese suicide prevention programs and may be insightful for other countries.

Attitudes towards suicide attempts broadcast on social media: an exploratory study of Chinese microblogs

Introduction. Broadcasting a suicide attempt on social media has become a public health concern in many countries, particularly in China. In these cases, social media users are likely to be the first to witness the suicide attempt, and their attitudes may determine their likelihood of joining rescue efforts. This paper examines Chinese social media (Weibo) users’ attitudes towards suicide attempts broadcast on Weibo. Methods. A total of 4,969 Weibo posts were selected from a customised Weibo User Pool which consisted of 1.06 million active users. The selected posts were then independently coded by two researchers using a coding framework that assessed: (a) Themes, (b) General attitudes, (c) Stigmatising attitudes, (d) Perceived motivations, and (e) Desired responses. Results and Discussion. More than one third of Weibo posts were coded as “stigmatising” (35%). Among these, 22%, 16%, and 15% of posts were coded as “deceitful,” “pathetic,” and “stupid,” respectively. Among the posts which reflected different types of perceived motivations, 57% of posts were coded as “seeking attention.” Among the posts which reflected desired responses, 37% were “not saving” and 28% were “encouraging suicide.” Furthermore, among the posts with negative desired responses (i.e., “not saving” and “encouraging suicide”), 57% and 17% of them were related to different types of stigmatising attitudes and perceived motivations, respectively. Specifically, 29% and 26% of posts reflecting both stigmatising attitudes and negative desired responses were coded as “deceitful” and “pathetic,” respectively, while 66% of posts reflecting both perceived motivations, and negative desired responses were coded as “seeking attention.” Very few posts “promoted literacy” (2%) or “provided resources” (8%). Gender differences existed in multiple categories. Conclusions. This paper confirms the need for stigma reduction campaigns for Chinese social media users to improve their attitudes towards those who broadcast their suicide attempts on social media. Results of this study support the need for improved public health programs in China and may be insightful for other countries and other social media platforms.

Suicide Communication on Social Media and Its Psychological Mechanisms: An Examination of Chinese Microblog Users

Background: This study aims to examine the characteristics of people who talk about suicide on Chinese microblogs (referred to as Weibo suicide communication (WSC)), and the psychological antecedents of such behaviors. Methods: An online survey was conducted on Weibo users. Differences in psychological and social demographic characteristics between those who exhibited WSC and those who did not were examined. Three theoretical models were proposed to explain the psychological mechanisms of WSC and their fitness was examined by Structural Equation Modeling (SEM). Results: 12.03% of our respondents exhibited WSC in the past 12 months. The WSC group was significantly younger and less educated, preferred using blogs and online forums for expressing themselves, and reported significantly greater suicide ideation, negative affectivity, and vulnerable personality compared to non-WSC users. SEM examinations found that Weibo users with higher negative affectivity or/and suicidal ideation, who were also using blogs and forums more, exhibited a significantly higher possibility of WSC. Conclusion: Weibo users who are at greater suicide risk are more likely to talk about suicide on Weibo. WSC is a sign of negative affectivity or suicide ideation, and should be responded to with emotional support and suicide prevention services.