Deep Learning Based Topic Identification and Categorization: Mining Diabetes-Related Topics on Chinese Health Websites

Chen, Xinhuan; Zhang, Yong; Xu, Jennifer; Xing, Chunxiao; Chen, Hsinchun

doi:10.1007/978-3-319-32025-0_30

Cited by 7 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To date, bbs.tnbz.com has more than 171,787 registered members, approximately 43,000 discussion threads, and over 7 million posts. The site's long history and large amount of data have attracted recent studies focusing on online health (Chen et al, 2016;Deng et al, 2018). The site is also well suited for examining chronic disease patients' social support acquisition over time.…”

Section: Methods 41 Data Collectionmentioning

confidence: 99%

Social support acquisition in online health communities: a social capital perspective

Liu

Lin²,

Jiang³

et al. 2022

INTR

View full text Add to dashboard Cite

PurposeThe authors empirically examined social capital factors affecting patients' social support acquisition with the aim of providing guidance to patients seeking social support online.Design/methodology/approachThe authors used social network analysis to extract data about social capital factors from online health communities and text mining to identify forms of informational support and emotional support grounded in online, text-based communication. Moreover, the authors employed a random coefficient model to understand the dynamic influence of social capital factors on both informational and emotional support.FindingsThe results from the empirical analyses show that structural connections have a lasting impact on the acquisition of both types of support; that is, social connections developed in the past will have an effect on the future. For relational capital, strong ties were less important; the quantity of connections mattered more than the quality when acquiring informational support. The use of health-related language increased the amount of informational support acquired. Over time, patients gained increasing social support, which primarily came from the patients' historical threads, likely via searches from peers facilitated by accumulated social capital.Originality/valueThe authors' research adds to the literature on social capital and social support in online health communities by exploring how the three dimensions of social capital affect social support acquisition. The authors' research also contributes to the online health care literature by examining social support from a dynamic perspective. Practically, the authors' findings provide guidance for patients on what decisions to make to acquire more social support.

show abstract

Section: Methods 41 Data Collectionmentioning

confidence: 99%

Social support acquisition in online health communities: a social capital perspective

Liu

Lin²,

Jiang³

et al. 2022

INTR

View full text Add to dashboard Cite

show abstract

“…Text classification is an important task of automatically classifying a set of documents into categories. It has been widely utilized to facilitate various kinds of crucial information retrieval, such as spam filtering systems [1] , recommender systems [2] , subject categorization [3] , and so on. Text classification also serves as the basis of numerous tasks [4][5][6] , thereby arousing natural concerns.…”

Section: Introductionmentioning

confidence: 99%

Supervised Contrastive Learning with Term Weighting for Improving Chinese Text Classification

Guo

Zhao

Liu

et al. 2023

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

With the rapid growth of information retrieval technology, Chinese text classification, which is the basis of information content security, has become a widely discussed topic. In view of the huge difference compared with English, Chinese text task is more complex in semantic information representations. However, most existing Chinese text classification approaches typically regard feature representation and feature selection as the key points, but fail to take into account the learning strategy that adapts to the task. Besides, these approaches compress the Chinese word into a representation vector, without considering the distribution of the term among the categories of interest. In order to improve the effect of Chinese text classification, a unified method, called Supervised Contrastive Learning with Term Weighting (SCL-TW), is proposed in this paper. Supervised contrastive learning makes full use of a large amount of unlabeled data to improve model stability. In SCL-TW, we calculate the score of term weighting to optimize the process of data augmentation of Chinese text. Subsequently, the transformed features are fed into a temporal convolution network to conduct feature representation. Experimental verifications are conducted on two Chinese benchmark datasets. The results demonstrate that SCL-TW outperforms other advanced Chinese text classification approaches by an amazing margin.

show abstract

Deep Learning Based Temporal Information Extraction Framework on Chinese Electronic Health Records

Tian

Xing

2018

Web Information Systems and Applications

View full text Add to dashboard Cite

Deep Learning Based Topic Identification and Categorization: Mining Diabetes-Related Topics on Chinese Health Websites

Cited by 7 publications

References 16 publications

Social support acquisition in online health communities: a social capital perspective

Social support acquisition in online health communities: a social capital perspective

Supervised Contrastive Learning with Term Weighting for Improving Chinese Text Classification

Deep Learning Based Temporal Information Extraction Framework on Chinese Electronic Health Records

Contact Info

Product

Resources

About