Using Hashtag Graph-Based Topic Model to Connect Semantically-Related Words Without Co-Occurrence in Microblogs

Wang, Yuan; Liu, Jie; Huang, Yalou; Xia, Feng

doi:10.1109/tkde.2016.2531661

Cited by 60 publications

(30 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For three authors, you may have to improvise. Frequency of Cooccurrence Words 7 [5], [27], [31][32][33][34][35][36] Pseudo documents 6 [22], [23], [36][37][38][39] Word weighting 6 [26], [40][41][42][43][44] Word Embedding 15 [31], [22], [26], [28][ [45][46][47][48][49][50][51][52][53][54][55][56] Sentence Level 1 [57] Hash tags 5 [23], [43], [46], [58], [59]…”

Section: Title and Authorsmentioning

confidence: 99%

“…Here tags serve as a probability distribution over themes. Wang et al, [59] proposed a model called HGTM (Hashtag Graph-based Topic Model) to reduce sparse and noise. HGTM uses tags relational knowledge to analyze the semantic relations between users and their hashtags to develop more reliable topics even if words are unavailable in the specific tweets.…”

Section: Topic Modeling On Short Textsmentioning

confidence: 99%

See 1 more Smart Citation

A Detailed Survey on Topic Modeling for Document and Short Text Data

Likhitha¹,

Junior²,

H.³

2019

IJCA

View full text Add to dashboard Cite

show abstract

Section: Title and Authorsmentioning

confidence: 99%

Section: Topic Modeling On Short Textsmentioning

confidence: 99%

A Detailed Survey on Topic Modeling for Document and Short Text Data

Likhitha¹,

Junior²,

H.³

2019

IJCA

View full text Add to dashboard Cite

show abstract

“…A novel hashtag graph-based topic model has been proposed to discover the topics of tweets. This model utilizes hashtag relation information in hashtag graphs and potent to understand the word semantic relations, even if the words have not co-occurred in a tweet (Wang et al, 2016).…”

Section: Trending Topics From News and Social Mediamentioning

confidence: 99%

Extracting scientific trends by mining topics from Call for Papers

Arshad

Bakar

Soroya

et al. 2019

LHT

View full text Add to dashboard Cite

Purpose The purpose of this paper is to present a novel approach for mining scientific trends using topics from Call for Papers (CFP). The work contributes a valuable input for researchers, academics, funding institutes and research administration departments by sharing the trends to set directions of research path. Design/methodology/approach The authors procure an innovative CFP data set to analyse scientific evolution and prestige of conferences that set scientific trends using scientific publications indexed in DBLP. Using the Field of Research code 804 from Australian Research Council, the authors identify 146 conferences (from 2006 to 2015) into different thematic areas by matching the terms extracted from publication titles with the Association for Computing Machinery Computing Classification System. Furthermore, the authors enrich the vocabulary of terms from the WordNet dictionary and Growbag data set. To measure the significance of terms, the authors adopt the following weighting schemas: probabilistic, gram, relative, accumulative and hierarchal. Findings The results indicate the rise of “big data analytics” from CFP topics in the last few years. Whereas the topics related to “privacy and security” show an exponential increase, the topics related to “semantic web” show a downfall in recent years. While analysing publication output in DBLP that matches CFP indexed in ERA Core A* to C rank conference, the authors identified that A* and A tier conferences not merely set publication trends, since B or C tier conferences target similar CFP. Originality/value Overall, the analyses presented in this research are prolific for the scientific community and research administrators to study research trends and better data management of digital libraries pertaining to the scientific literature.

show abstract

“…As a consequence, within Twitter analytics, hashtags are used to define what is 'trending' or 'viral', and other forms of big data mining on social media likewise use hashtags as analytical tools for modelling topics and tracking participant engagement and involvement (e.g. Blaszka, Burch, Frederick, Clavio, & Walsh, 2012;Wang, Liu, Huang, & Feng, 2016).…”

Section: Hashtags and Translingualismmentioning

confidence: 99%

Formatting online actions: #justsaying on Twitter

Blommaert

2019

International Journal of Multilingualism

View full text Add to dashboard Cite

The hashtag #justsaying is one of Twitter's global stock hashtags. The hashtag is nontopical and appears to fulfil a complex range of metapragmatic framing functions. In this paper, I shall look at Dutch-language tweets in which the hashtag is being used as a fully enregistered 'translingual' framing device, and I will attempt an analysis focused on the specific kinds of communicative actions it marks and organises. I shall use the notion of formatting as the point of departure: hashtags, as part of an innovative online scripted register, can be seen as formatting devices that introduce, proleptically, a recognisable framing effect on the statement (the tweet), often as a reframing response to other statements giving keys for complex and multiple but equally formatted forms of uptake. The hashtag, thus, appears to have powerful interactional structuring effects in formatting specific lines of action.

show abstract

Using Hashtag Graph-Based Topic Model to Connect Semantically-Related Words Without Co-Occurrence in Microblogs

Cited by 60 publications

References 30 publications

A Detailed Survey on Topic Modeling for Document and Short Text Data

A Detailed Survey on Topic Modeling for Document and Short Text Data

Extracting scientific trends by mining topics from Call for Papers

Formatting online actions: #justsaying on Twitter

Contact Info

Product

Resources

About