Multi-View Unsupervised User Feature Embedding for Social
            Media-based Substance Use Prediction

Ding, Tao; Bickel, Warren K.; Pan, Shimei

doi:10.18653/v1/d17-1241

Cited by 37 publications

(19 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although some previous studies have provided intriguing approaches to learning representations at the level of words Mikolov, Yih, and Zweig 2013), sentences (Le and Mikolov 2014), and paragraphs (Kiros et al 2015), they are limited in modeling social media content with colloquial relations. Following similar ideas in this work, where discourse and topics are jointly explored, we can conduct other types of representation learning, e.g., embeddings for words (Li et al 2017b), messages (Dhingra et al 2016), or users (Ding, Bickel, and Pan 2017), in context of conversations, which should complement social media representation learning and vice versa.…”

Section: Discussionmentioning

confidence: 99%

A Joint Model of Conversational Discourse and Latent Topics on Microblogs

Yan

Wei

et al. 2018

Computational Linguistics

View full text Add to dashboard Cite

Conventional topic models are ineffective for topic extraction from microblog messages, because the data sparseness exhibited in short messages lacking structure and contexts results in poor message-level word co-occurrence patterns. To address this issue, we organize microblog messages as conversation trees based on their reposting and replying relations, and propose an unsupervised model that jointly learns word distributions to represent: 1) different roles of conversational discourse, 2) various latent topics in reflecting content information. By explicitly distinguishing the probabilities of messages with varying discourse roles in containing topical words, our model is able to discover clusters of discourse words that are indicative of topical content. In an automatic evaluation on large-scale microblog corpora, our joint model yields topics with better coherence scores than competitive topic models from previous studies. Qualitative analysis on model outputs indicates that our model induces meaningful representations for both discourse and topics. We further present an empirical study on microblog summarization based on the outputs of our joint model. The results show that the jointly modeled discourse and topic representations can effectively indicate summary-worthy content in microblog conversations.

show abstract

Section: Discussionmentioning

confidence: 99%

A Joint Model of Conversational Discourse and Latent Topics on Microblogs

Yan

Wei

et al. 2018

Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…25 National survey on drug use and health in 2014 reported that 1 in 10 Americans waged 12 or older had disorders of substances use. 26,27 In the recent years, mass media sites like Facebook, Myspace, and YouTube have grown rapidly to share information to larger population.…”

Section: Media a N D Substances Usementioning

confidence: 99%

Role of Mass Media on Mankind: Time to Rethink

Jelly¹,

Choudhary²,

Sharma³

et al. 2021

Pondicherry Journal of Nursing

View full text Add to dashboard Cite

In the era of 21st century, mass media is important part of everyone's life which includes e-mails, online marketing, education sites, etc. Media and computer facilitated new skills that enable the formation and discussion of ideas, problems, data, and views and in another way of presence via network and communities. This review covers all features of mass media with its positive as well as negative aspects. With the emphasis of media on areas such as education, community, children, adolescent, obesity, sexuality, and business, etc., therefore, this research review describes how mass media will comprehensively affect all aspects. Since 2000, mass media has blossomed to prospect and is still growing limitlessly sideways with media sharing, and several other entries that offered real-time updates were announced by the example of Twitter, Facebook, etc. It has become the vital part of everyone's life. Search strategy: Articles were extracted using MESH keywords, such as children, adolescents, human, electronic mail, mass media, marketing, and health education, etc., from Embase, PubMed, and Google Scholar search engine. For additional information, we also used literature to obtain information on mass media impact in several fields. Mass media use has grown up exponentially over the past era, and this growth is expected to continue. It has a drastic impact on lives of all age-groups. Mass media is an essential or significant force in this modern civilization which has an impact on several aspects of human life. Overall, mass media has both positive effects and negative effects, but overuse of mass media may lead to a tendency of antisocial behavior.

show abstract

“…For tasks other than personality prediction, several studies leverage the textual information derived from user behaviors in social media. Ding et al (2017) applied texts that users liked and posted to predict substance users such as people who drink alcohol. They showed that the distributed bag-of-words (DBOW) models (Le and Mikolov, 2014) achieve good performance.…”

Section: Related Workmentioning

confidence: 99%

“…The first model uses them as BOW features of the SVM classifier and the second model further applies SVD. The third model is a model using DBOW proposed by Ding et al (2017). This model uses words that have appeared ten or more times.…”

Section: Use Of Textual Informationmentioning

confidence: 99%

Incorporating Textual Information on User Behavior for Personality Prediction

Yamada

Sasano

Takeda

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop

View full text Add to dashboard Cite

Several recent studies have shown that textual information of user posts and user behaviors such as liking and sharing the specific posts are useful for predicting the personality of social media users. However, less attention has been paid to the textual information derived from the user behaviors. In this paper, we investigate the effect of textual information on user behaviors for personality prediction. Our experiments on the personality prediction of Twitter users show that the textual information of user behaviors is more useful than the cooccurrence information of the user behaviors. They also show that taking user behaviors into account is crucial for predicting the personality of users who do not post frequently.

show abstract

Multi-View Unsupervised User Feature Embedding for Social Media-based Substance Use Prediction

Cited by 37 publications

References 36 publications

A Joint Model of Conversational Discourse and Latent Topics on Microblogs

A Joint Model of Conversational Discourse and Latent Topics on Microblogs

Role of Mass Media on Mankind: Time to Rethink

Incorporating Textual Information on User Behavior for Personality Prediction

Contact Info

Product

Resources

About