Automated Generation of Latent Topics on Emerging Technologies from YouTube Video Content

Daniel, Clinton; Dutta, Kaushik

doi:10.24251/hicss.2018.222

Cited by 4 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By applying the algorithm or proposed tools to a real‐life dataset, authors discussed their perceived value of the automatically mined or extracted data. In the field of mining emerging health technologies, for example, it was a common approach to train Latent Dirichlet Distribution (LDA) topic model algorithms to identify dominant themes in large corpora of data 47,54,60–62 . This approach is chosen because LDA is a generative unsupervised machine‐learning approach, assigning a pre‐defined number of topics to each document and using probability distributions across the vocabulary to assign words to topics 63 .…”

Section: Resultsmentioning

confidence: 99%

“…In the field of mining emerging health technologies, for example, it was a common approach to train Latent Dirichlet Distribution (LDA) topic model algorithms to identify dominant themes in large corpora of data. 47,54,[60][61][62] This approach is chosen because LDA is a generative unsupervised machine-learning approach, assigning a pre-defined number of topics to each document and using probability distributions across the vocabulary to assign words to topics. 63 The output of this algorithm is a set of unlabelled word-clouds with vocabulary that may have emergent semantic similarities when examined by a human.…”

Section: Evaluation Of Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Automated data analysis of unstructured grey literature in health research: A mapping review

Schmidt,

Mohamed,

Meader

et al. 2023

Research Synthesis Methods

View full text Add to dashboard Cite

The amount of grey literature and ‘softer’ intelligence from social media or websites is vast. Given the long lead‐times of producing high‐quality peer‐reviewed health information, this is causing a demand for new ways to provide prompt input for secondary research. To our knowledge, this is the first review of automated data extraction methods or tools for health‐related grey literature and soft data, with a focus on (semi)automating horizon scans, health technology assessments (HTA), evidence maps, or other literature reviews. We searched six databases to cover both health‐ and computer‐science literature. After deduplication, 10% of the search results were screened by two reviewers, the remainder was single‐screened up to an estimated 95% sensitivity; screening was stopped early after screening an additional 1000 results with no new includes. All full texts were retrieved, screened, and extracted by a single reviewer and 10% were checked in duplicate. We included 84 papers covering automation for health‐related social media, internet fora, news, patents, government agencies and charities, or trial registers. From each paper, we extracted data about important functionalities for users of the tool or method; information about the level of support and reliability; and about practical challenges and research gaps. Poor availability of code, data, and usable tools leads to low transparency regarding performance and duplication of work. Financial implications, scalability, integration into downstream workflows, and meaningful evaluations should be carefully planned before starting to develop a tool, given the vast amounts of data and opportunities those tools offer to expedite research.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Evaluation Of Algorithmsmentioning

confidence: 99%

Automated data analysis of unstructured grey literature in health research: A mapping review

Schmidt,

Mohamed,

Meader

et al. 2023

Research Synthesis Methods

View full text Add to dashboard Cite

show abstract

“…By applying the algorithm or proposed tools to a real-life dataset, authors discussed their perceived value of the automatically mined or extracted data. In the field of mining emerging health technologies, for example, it was a common approach to train Latent Dirichlet Distribution (LDA) topic model algorithms to identify dominant themes in large corpora of data (Daniel & Dutta, 2018;Guo et al, 2017;Sofean & Aras, 2018;Zhao et al, 2017;Zhou et al, 2021). This approach is chosen because LDA is a generative unsupervised machine-learning approach, assigning a pre-defined number of topics to each document and using probability distributions across the vocabulary to assign words to topics (Blei et al, 2003).…”

Section: Metrics and Strategies Used For The Evaluation Of Algorithmsmentioning

confidence: 99%

Automated data extraction of unstructured grey literature in health research: a mapping review of the current research literature

Schmidt

Mohamed

Meader

et al. 2023

Preprint

View full text Add to dashboard Cite

The amount of grey literature and "softer" intelligence from social media or websites is vast. Given the long lead-times of producing high-quality peer-reviewed health information this is causing a demand for new ways to provide prompt input for secondary research. To our knowledge this is the first review of automated data extraction methods or tools for health-related grey literature and soft intelligence, with a focus on (semi)automating horizon scans, health technology assessments, evidence maps, or other literature reviews. We searched six databases to cover both health- and computer-science literature. After deduplication, 10% of the search results were screened by two reviewers, the remainder was single-screened up to an estimated 95% sensitivity; screening was stopped early after screening an additional 1000 results with no new includes. All full texts were retrieved, screened, and extracted by a single reviewer and 10% were checked in duplicate. We included 84 papers covering automation for health-related social media, internet fora, news, patents, government agencies and charities, or trial registers. From each paper we answered three research questions: Firstly, important functionalities for users of the tool or method; secondly, information about the level of support and reliability; and thirdly, practical challenges and research gaps. Poor availability of code, data, and usable tools leads to low transparency regarding performance and duplication of work. Financial implications, scalability, integration into downstream workflows, and meaningful evaluations should be carefully planned before starting to develop a tool, given the vast amounts of data and opportunities those tools offer to expedite research.

show abstract

“…LDA is one of the methods used in identifying the topic of contents from video titles and video comments. Several studies have been conducted on identifying the topic of content on You-Tube videos using the LDA method (28)(29)(30). Our research adopts LDA to predict titles according to the titles of YouTube videos.…”

Section: Latent Dirichlet Allocationmentioning

confidence: 99%

Evaluating YouTube as a source of information on COVID-19: analysis with latent Dirichlet allocation method

Doğaner¹,

Zhang²

2021

BLL

View full text Add to dashboard Cite

OBJECTIVE: The global impact of COVID-19 pandemic has gained momentum rapidly. People have little information about SARS-CoV-2 (Coronavirus). Internet has become a frequently used tool to obtain information in recent years, while YouTube is one of the popular sources of information with many videos on its platform. This study aims to identify the topics regarding Coronavirus that people learned about on YouTube. The videos about Coronavirus were also evaluated in terms of the reliability of their source of information. METHODS: In total, 160 videos on Coronavirus that had 500,000 or more views were analysed. The latent Dirichlet allocation method was used in the process of identifying the topics that were then compared in terms of video parameters. The reliability of the source of information provided by videos was assessed with a modifi ed DISCERN tool. RESULTS: A proportion of 15.6 % of these videos had a scientifi c content, while 45 % of these videos were about the process entailed by the COVID-19 pandemic. In terms of video reliability, the difference between video types was found to be signifi cant; videos with scientifi c content had more reliable sources of information (p<0.001). CONCLUSION: It has been determined that the videos about the symptoms, diagnosis and treatment of COVID-19, and those with scientifi c content have the most reliable source of information on Coronavirus

show abstract

Automated Generation of Latent Topics on Emerging Technologies from YouTube Video Content

Abstract: Abstract

Cited by 4 publications

References 10 publications

Automated data analysis of unstructured grey literature in health research: A mapping review

Automated data analysis of unstructured grey literature in health research: A mapping review

Automated data extraction of unstructured grey literature in health research: a mapping review of the current research literature

Evaluating YouTube as a source of information on COVID-19: analysis with latent Dirichlet allocation method

Contact Info

Product

Resources

About