The main trends for multi-tier supply chain in Industry 4.0 based on Natural Language Processing

Zhou, Rongyan; Awasthi, Anjali; Cardinal, Julie Stal-Le

doi:10.1016/j.compind.2020.103369

Cited by 28 publications

(8 citation statements)

References 170 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, a few topics ensured explicability and efficient analysis of each topic. We consider the best number of topics to correspond to the best c_v coherence value, which is consistent with several studies, including Zhou et al (2020) and Fang and Partovi (2020). In addition, if a coherence peak that includes the highest coherence value is shared by the LDA runs with different optimization interval values, it is considered to indicate the best number of topics.…”

Section: Lda Modelingmentioning

confidence: 81%

“…Mallet's underlying approach relies on Gibbs sampling, which has well-known implications for runtime complexity (Jelodar et al, 2020) because the training process requires keeping the entire dataset in memory. However, as shown by Zhou et al (2020), Mallet performs better than Gensim from the perspective of coherence value. Coherence roughly reflects the degree of mutual support between subsets (word sets) within each topic in a topic model.…”

Section: Lda Modelingmentioning

confidence: 91%

See 1 more Smart Citation

Promoting Techno-Scientific Biomedical Communication in Russia: Pro-government Non-profit Organizations

Marchenko¹,

Bykov²

2022

Front. Commun.

View full text Add to dashboard Cite

The rapidly expanding e-health market tends to reinvent the roles of science, entrepreneurship, and state. However, the results of such reinvention remain unclear. This study investigates the decade-long history (2011–2021) of the promotion of techno-scientific biomedical communication by pro-government non-profit organizations in Russia. In 2021, the World Bank pointed out that digital technologies have played a critical role in the pandemic in Russia and Russia's economic recovery is gathering pace. Thus, Russia tends to correspond to many other emerging health markets. We compare texts from non-profit organizations' websites and Facebook accounts with official state actions and the national mass media health agenda. The instruments that were used for text mining were topic modeling with latent Dirichlet allocation and an algorithm for keyphrase relationship visualization. The results revealed that promotion started no later than 2011 as a general private initiative in health. Throughout the state reforms and geopolitical crisis of 2014, in 2017–2019 digitalization was finally chosen as a model for the healthcare system. Simultaneously, the idea of digital reform for the health system was disseminated by the mass media. The pandemic drew attention to this communication, but it did not create significant change. Pro-government non-profit organizations continue to promote new directions for biomedical communication in Russia.

show abstract

Section: Lda Modelingmentioning

confidence: 81%

Section: Lda Modelingmentioning

confidence: 91%

Promoting Techno-Scientific Biomedical Communication in Russia: Pro-government Non-profit Organizations

Marchenko¹,

Bykov²

2022

Front. Commun.

View full text Add to dashboard Cite

show abstract

“…LDA is a particularly popular parametric approach that models documents as mixtures of topics and topics as mixtures of words (probabilistic distributions over words). An overview of recent papers reporting the application of two widely used LDA-based packages, namely Java-based Mallet 4 [Zhou, Awasthi, Cardinal, 2020;Fang, Partovi, 2021;Cho, Park, Song, 2020] and Python-based Gensim 5 [Porter, 2018;Kastrati, Kurti, Imran, 2020;Riesener et al, 2019], as well as extensive experiments with both packages on the 1st-week data (LJ) followed by the analysis of LDAvis [Sievert, Shirley, 2014] output, we settled on the use of the Mallet package [Mimno et al, 2011]. Ebeid and Arango 6 compare both tools and point out that both have their strengths and weaknesses.…”

Section: Latent Dirichlet Allocationmentioning

confidence: 99%

A Pipeline for Graph-Based Monitoring of the Changes in the Information Space of Russian Social Media during the Lockdown

Danilova¹,

Popova²,

Карпова³

2021

MONITORING OF PUBLIC OPINION

View full text Add to dashboard Cite

With the COVID-19 outbreak and the subsequent lockdown, social media became a vital communication tool. The sudden outburst of online activity influenced information spread and consumption patterns. It increases the relevance of studying the dynamics of social networks and developing data processing pipelines that allow a comprehensive analysis of social media data in the temporal dimension. This paper scopes the weekly dynamics of the information space represented by Russian social media (Twitter and LiveJournal) during a critical period (massive COVID-19 outbreak and first governmental measures). The approach is twofold: 1) build the time series of topic similarity indicators by identifying COVID-related topics in each week and measuring user contribution to the topic space, and 2) cluster user activity and display user-topic relationships on graphs in a dashboard application. The paper describes the development of the pipeline, explains the choices made and provides a case study of the adaptation to virus control measures. The results confirm that social processes and behavior in response to pandemic-triggered changes can be successfully traced in social media. Moreover, the adaptation trends revealed by psychological and sociological studies are reflected in our data and can be explored using the proposed method.

show abstract

“…Research on the development of the LDA model using the MAchine Learning for LanguagE Toolkit (Mallet) is also a reference in this study. The topic modelling using LDA with Mallet provided a higher coherence score evaluation value than LDA methods with standard Gensim packages in grouping topics in documents in the form of related articles "multi-tier supply chain in Industry 4.0" [10]. The implementation of topic modelling using LDA with Mallet successfully grouped ten topics related to job trends in the information technology sector based on the information available on "LinkedIn" [11].…”

Section: Introductionmentioning

confidence: 99%

Topic Modelling in Knowledge Management Documents BPS Statistics Indonesia

Hendrawan¹,

Projo²

2022

icdsos

View full text Add to dashboard Cite

Knowledge management is an important activity in improving the performance an organization. BPS Statistics Indonesia has recently implemented such a system to improve the quality and efficiency of business processes. The purposes of this research are: 1) implementing topic modelling on BPS Knowledge Management System to identify groups of document topics; 2) providing recommendations on which the best topic modelling; 3) building a web service function of topic modelling for BPS that includes data preprocessing function and topic group recommendation function. This study applies the Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA) topic modelling methods to determine the best grouping techniques for knowledge management systems in BPS Statistics Indonesia. The results show that the LDA model using Mallet is the best model with 25 topic groups and a coherence score of 0.4803. The performance result suggest that the best modelling method is the LDA. The LDA model is then successfully implemented in RESTful web service to provide services in the preprocessing function and topic recommendations on documents entered into the Knowledge Management System BPS.

show abstract

The main trends for multi-tier supply chain in Industry 4.0 based on Natural Language Processing

Cited by 28 publications

References 170 publications

Promoting Techno-Scientific Biomedical Communication in Russia: Pro-government Non-profit Organizations

Promoting Techno-Scientific Biomedical Communication in Russia: Pro-government Non-profit Organizations

A Pipeline for Graph-Based Monitoring of the Changes in the Information Space of Russian Social Media during the Lockdown

Topic Modelling in Knowledge Management Documents BPS Statistics Indonesia

Contact Info

Product

Resources

About