An Uncertainty-Aware Approach for Exploratory Microblog Retrieval.

Although there has been a great deal of interest in analyzing customer opinions and breaking news in microblogs, progress has been hampered by the lack of an effective mechanism to discover and retrieve data of interest from microblogs. To address this problem, we have developed an uncertainty-aware visual analytics approach to retrieve salient posts, users, and hashtags. We extend an existing ranking technique to compute a multifaceted retrieval result: the mutual reinforcement rank of a graph node, the uncertainty of each rank, and the propagation of uncertainty among different graph nodes. To illustrate the three facets, we have also designed a composite visualization with three visual components: a graph visualization, an uncertainty glyph, and a flow map. The graph visualization with glyphs, the flow map, and the uncertainty analysis together enable analysts to effectively find the most uncertain results and interactively refine them. We have applied our approach to several Twitter datasets. Qualitative evaluation and two real-world case studies demonstrate the promise of our approach for retrieving high-quality microblog data.

Examining Accumulated Emotional Traits in Suicide Blogs With an Emotion Topic Model.

Suicide has been a major cause of death throughout the world. Recent studies have proved a reliable connection between the emotional traits and suicide. However, detection and prevention of suicide are mostly carried out in the clinical centers, which limit the effective treatments to a restricted group of people. To assist detecting suicide risks among the public, we propose a novel method by exploring the accumulated emotional information from people's daily writings (i.e., Blogs), and examining these emotional traits that are predictive of suicidal behaviors. A complex emotion topic model is employed to detect the underlying emotions and emotion-related topics in the Blog streams, based on eight basic emotion categories and five levels of emotion intensities. Since suicide is caused through an accumulative process, we propose three accumulative emotional traits, i.e., accumulation, covariance, and transition of the consecutive Blog emotions, and employ a generalized linear regression algorithm to examine the relationship between emotional traits and suicide risk. Our experiment results suggest that the emotion transition trait turns to be more discriminative of the suicide risk, and that the combination of three traits in linear regression would generate even more discriminative predictions. A classification of the suicide and nonsuicide Blog articles in our additional experiment verifies this result. Finally, we conduct a case study of the most commonly mentioned emotion-related topics in the suicidal Blogs, to further understand the association between emotions and thoughts for these authors.

Event-based user classification in Weibo media.

Weibo media, known as the real-time microblogging services, has attracted massive attention and support from social network users. Weibo platform offers an opportunity for people to access information and changes the way people acquire and disseminate information significantly. Meanwhile, it enables people to respond to the social events in a more convenient way. Much of the information in Weibo media is related to some events. Users who post different contents, and exert different behavior or attitude may lead to different contribution to the specific event. Therefore, classifying the large amount of uncategorized social circles generated in Weibo media automatically from the perspective of events has been a promising task. Under this circumstance, in order to effectively organize and manage the huge amounts of users, thereby further managing their contents, we address the task of user classification in a more granular, event-based approach in this paper. By analyzing real data collected from Sina Weibo, we investigate the Weibo properties and utilize both content information and social network information to classify the numerous users into four primary groups: celebrities, organizations/media accounts, grassroots stars, and ordinary individuals. The experiments results show that our method identifies the user categories accurately.

Sublanguage analysis of medical weblogs.

Analysing medical social media data gains in importance given an increased availability of such data. In this paper, we analyse the language of medical blogs by means of a sublanguage analysis. More specifically, verb usage, semantic categories of used words as well as co-occurrence patterns are determined by means of natural language processing tools. The results show that in this text type, many concepts refer to the semantic categories Living Beings and Chemicals and Drugs. In contrast to clinical documents, the spectrum of verbs in blogs is very broad creating semantic relations of different types. From these language characteristics, we conclude for automatic processing tools for medical blogs that methods for reference resolution and for relation extraction where the relation type does not need to be specified in advance are required.

Predicting active users' personality based on micro-blogging behaviors.

Because of its richness and availability, micro-blogging has become an ideal platform for conducting psychological research. In this paper, we proposed to predict active users' personality traits through micro-blogging behaviors. 547 Chinese active users of micro-blogging participated in this study. Their personality traits were measured by the Big Five Inventory, and digital records of micro-blogging behaviors were collected via web crawlers. After extracting 839 micro-blogging behavioral features, we first trained classification models utilizing Support Vector Machine (SVM), differentiating participants with high and low scores on each dimension of the Big Five Inventory [corrected]. The classification accuracy ranged from 84% to 92%. We also built regression models utilizing PaceRegression methods, predicting participants' scores on each dimension of the Big Five Inventory. The Pearson correlation coefficients between predicted scores and actual scores ranged from 0.48 to 0.54. Results indicated that active users' personality traits could be predicted by micro-blogging behaviors.

Research blogs and the discussion of scholarly information.

The research blog has become a popular mechanism for the quick discussion of scholarly information. However, unlike peer-reviewed journals, the characteristics of this form of scientific discourse are not well understood, for example in terms of the spread of blogger levels of education, gender and institutional affiliations. In this paper we fill this gap by analyzing a sample of blog posts discussing science via an aggregator called ResearchBlogging.org (RB). ResearchBlogging.org aggregates posts based on peer-reviewed research and allows bloggers to cite their sources in a scholarly manner. We studied the bloggers, blog posts and referenced journals of bloggers who posted at least 20 items. We found that RB bloggers show a preference for papers from high-impact journals and blog mostly about research in the life and behavioral sciences. The most frequently referenced journal sources in the sample were: Science, Nature, PNAS and PLoS One. Most of the bloggers in our sample had active Twitter accounts connected with their blogs, and at least 90% of these accounts connect to at least one other RB-related Twitter account. The average RB blogger in our sample is male, either a graduate student or has been awarded a PhD and blogs under his own name.

Development of a researcher codebook for use in evaluating social networking site profiles.

INTRODUCTION: Social networking sites (SNSs) are immensely popular and allow for the display of personal information, including references to health behaviors. Evaluating displayed content on an SNS for research purposes requires a systematic approach and a precise data collection instrument. The purpose of this article is to describe one approach to the development of a research codebook so that others may develop and test their own codebooks for use in SNS research. METHODS: Our SNS research codebook began on the basis of health behavior theory and clinical criteria. Key elements in the codebook developmental process included an iterative team approach and an emphasis on confidentiality. RESULTS: Codebook successes include consistently high inter-rater reliability. Challenges include time investment in coder training and SNS server changes. CONCLUSION: We hope that this article will provide detailed information about one systematic approach to codebook development so that other researchers may use this structure to develop and test their own codebooks for use in SNS research.

Analysis of pharmacy-centric blogs: Types, discourse themes, and issues.

OBJECTIVES: To determine types of pharmacy blogs in existence, themes of discourse on pharmacy blogs, and impressions of the profession generated by pharmacy blogs. DESIGN: Descriptive, qualitative, cross-sectional study. SETTING: Weblogs (blogs) on the World Wide Web in July 2009. PARTICIPANTS: Not applicable; pharmacy-centric blogs were analyzed. INTERVENTION: Qualitative research methods were used to form categories and assign pharmacy-centric blogs to appropriate categories. Thematic analysis was used to study the discourse of blogs in the personal views category. Finally, blogs in the personal views category were analyzed further to determine what type of impression (positive, negative, or neutral) they gave the reader. MAIN OUTCOME MEASURES: Categories, themes, and impressions of blogs, as determined by analysis. RESULTS: 136 blogs met study criteria. Seven main categories of pharmacy blogs emerged from the study. The majority of blogs were assigned to the news (n = 44) and personal views (n = 38) categories. Thematic analysis of blogs in the personal views category revealed 11 different themes. The top four blog post themes were issues with patients (n = 30), personal lives (n = 29), working conditions/issues (n = 20), and issues with other professionals (n = 19). A total of 24 (63%) blogs in the personal views category were judged as promoting a negative impression of pharmacists and/or the profession. CONCLUSION: The pharmacy blogosphere contains a variety of blog types. Most of these blogs studied were useful information resources for those in or considering the profession. However, a considerable number of pharmacy blogs contained derogatory posts regarding patients, other health care professionals, and/or the author's occupation as a pharmacist. Blogs such as these tend to generate a negative impression of pharmacy to the reader. The opportunity exists for pharmacists and pharmacy educators to use social media applications such as blogs to educate new pharmacists and advance the profession.