Concept over time: the combination of probabilistic topic model with wikipedia knowledge

Liang, Yao; Zhang, Yin; Wei, Baogang; Li, Lei; Wu, Fei; Zhang, Peng; Bian, Yali

doi:10.1016/j.eswa.2016.04.014

Cited by 23 publications

(8 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To track how topics evolve over different stages of the pandemic, we use dynamic topic model (DTM). This technique can capture dynamic evolution of topics from time-sequentially organized documents (Yao et al, 2016). DTM assumes that documents are divided by time slices, each of which is modeled with K-component topic model, where topics associated with time slice t evolve from those associated with the slice t À 1.…”

Section: Classifying Service Quality Attributesmentioning

confidence: 99%

“…As two popular topic modeling techniques, latent Dirichlet allocation (LDA) and structural topic model (STM) have been used to identify service quality attributes from online reviews (Ding et al , 2020; Ju et al , 2019; Lee and Yu, 2018). Both the two techniques assume static structure; however, they are not applicable in modelling dynamic nature of large sets of texts that are collected over time (Yao et al , 2016). These techniques are incapable of reflecting the dynamic nature of online reviews that are time-sequentially organized.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploring dynamic effects on classifying service quality attributes under the impacts of COVID-19 with evidence from online reviews

Nie

Chin²,

Tian³

et al. 2022

IJCHM

View full text Add to dashboard Cite

Purpose The purpose of this paper is exploring the effects of segment dynamic and temporal dynamic triggered by the COVID-19 pandemic on classifying service quality attributes, thereby formulating improvement strategies to satisfy customers and respond to threats. Design/methodology/approach Given the dynamics of the attractive quality theory, this paper designs a framework with four phases by embedding techniques of text mining and deep learning based on evidence from online reviews. Findings This paper figures out dynamics of service quality attributes for distinct segments and their dynamic proportion along with different stages of the pandemic. Another finding demonstrates segment dynamic and temporal dynamic effects of sentiments toward service quality attributes on customer satisfaction under the impacts of pandemic. Classification results and improvement strategies are derived for varying segments at different pandemic situations. Practical implications This paper reveals dynamic effects on classifying service quality attributes, which contributes to assisting hospitality practitioners from different segments in improving service quality when facing with the challenges of crisis and potential risks. Originality/value Given hospitality industry is time- and segment-sensitive, the authors achieve the quantification of dynamics of attractive quality theory and extend it into hospitality marketing and crisis management from the perspective of dynamics with evidence from online reviews.

show abstract

Section: Classifying Service Quality Attributesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Exploring dynamic effects on classifying service quality attributes under the impacts of COVID-19 with evidence from online reviews

Nie

Chin²,

Tian³

et al. 2022

IJCHM

View full text Add to dashboard Cite

show abstract

“…Model with Time Factor. Yao et al [18] revealed the semantic change process of words by correlating the time factor with Wikipedia text knowledge. In terms of event evolution, the associative topic model (ATM) is proposed [19], and the recognized cluster is represented as the word distribution of the cluster with the corresponding event.…”

Section: Research On Topicmentioning

confidence: 99%

Research on Sentiment Tendency and Evolution of Public Opinions in Social Networks of Smart City

Liu

Chen³

2020

Complexity

View full text Add to dashboard Cite

With the rapid development of mobile Internet, the social network has become an important platform for users to receive, release, and disseminate information. In order to get more valuable information and implement effective supervision on public opinions, it is necessary to study the public opinions, sentiment tendency, and the evolution of the hot events in social networks of a smart city. In view of social networks’ characteristics such as short text, rich topics, diverse sentiments, and timeliness, this paper conducts text modeling with words co-occurrence based on the topic model. Besides, the sentiment computing and the time factor are incorporated to construct the dynamic topic-sentiment mixture model (TSTS). Then, four hot events were randomly selected from the microblog as datasets to evaluate the TSTS model in terms of topic feature extraction, sentiment analysis, and time change. The results show that the TSTS model is better than the traditional models in topic extraction and sentiment analysis. Meanwhile, by fitting the time curve of hot events, the change rules of comments in the social network is obtained.

show abstract

“…Finally, factorial LDA has a mathematical setup similar to that of the structural topic model but focuses on latent covariates with an emphasis on interpretation (27). For details on current development of various topic models, see Yao et al (28). In the current study, a web portal was developed to provide interested readers with a detailed bibliography on text mining and topic modeling (29).…”

Section: Literature Reviewmentioning

confidence: 99%

Trends in Transportation Research

Das¹,

Dixon²,

Sun

et al. 2017

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Proceedings of journal and conference papers are good sources of big textual data to examine research trends in various branches of science. The contents, usually unstructured in nature, require fast machine-learning algorithms to be deciphered. Exploratory analysis through text mining usually provides the descriptive nature of the contents but lacks quantification of the topics and their correlations. Topic models are algorithms designed to discover the main theme or trend in massive collections of unstructured documents. Through the use of a structural topic model, an extension of latent Dirichlet allocation, this study introduced distinct topic models on the basis of the relative frequencies of the words used in the abstracts of 15,357 TRB compendium papers. With data from 7 years (2008 through 2014) of TRB annual meeting compendium papers, the 20 most dominant topics emerged from a bag of 4 million words. The findings of this study contributed to the understanding of topical trends in the complex and evolving field of transportation engineering research.

show abstract

Concept over time: the combination of probabilistic topic model with wikipedia knowledge

Cited by 23 publications

References 2 publications

Exploring dynamic effects on classifying service quality attributes under the impacts of COVID-19 with evidence from online reviews

Exploring dynamic effects on classifying service quality attributes under the impacts of COVID-19 with evidence from online reviews

Research on Sentiment Tendency and Evolution of Public Opinions in Social Networks of Smart City

Trends in Transportation Research

Contact Info

Product

Resources

About