Topic Modeling of Document Metadata for Visualizing Collaborations over Time

Chen, Francine; Chiu, Patrick; Lim, Seongtaek

doi:10.1145/2856767.2856787

Cited by 10 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…В статье рассматривается тематическое моделирование как одно из эффективных направлений в области автоматизированной обработки текстов на естественном языке [1]. Актуальность проблем автоматизированного анализа текстов обоснована как отечественными учеными [2][3][4], так и в трудах зарубежных авторов [5,6].…”

Section: Doi 1014258/izvasu(2020)1-10unclassified

Computer Methods for Thematic Modeling of Textbooks Collection in Natural Language

et al. 2020

View full text Add to dashboard Cite

The paper presents the development results of computer methods for analyzing text data and assessing classification inaccuracies at the stages of thematic modeling. This study uses as an example the task to process textual data of a collection of graduate qualification works prepared and defended by students of Altai State University, Faculty of Mathematics and IT in recent years. The main results obtained in the paper are listed as follows. Relevant application areas and directions for computer methods and thematic modeling in the educational process are identified. Justification of the general algorithm for solving the problem of the thematic analysis of collections of educational materials is carried out. Information technologies for thematic modeling are developed, and estimation of analysis errors on a set of test documents is obtained. It is shown that computer-based methods of thematic modeling and information technology to support them can be used both in the educational process and in the development of educational and methodological documents.

show abstract

Section: Doi 1014258/izvasu(2020)1-10unclassified

Computer Methods for Thematic Modeling of Textbooks Collection in Natural Language

et al. 2020

View full text Add to dashboard Cite

show abstract

“…1,50,000 words). Therefore, motivated by advocacy in recent work [26,12,13,6,7] for combining topic modeling [9] and qualitative reading to analyze free-text survey questions, this study used the Latent Dirichlet allocation (LDA) model [43], the most commonly used topic model in HCI and related communities, along with close inductive qualitative reading, to identify the underlying themes and label "topics" identified by the model. Specifically, LDA is an unsupervised computational approach in which documents (in context of our study, the responses to open-ended questions) are represented as random mixtures of latent topics, where each "topic" is characterized by a distribution of words [9] that summarizes the main themes in the documents.…”

Section: Content Analysismentioning

confidence: 99%

An Analysis of (Non-)Use Practices and Decisions of Internet of Things

Garg

2019

Human-Computer Interaction – INTERACT 2019

View full text Add to dashboard Cite

Recent market reports have suggested that adoption of the Internet of Things (IoT) does not always lead to long-term use. This paper aims to advance an understanding of the sociological process of the (non-)use of the IoT. To this end, we present results from a mixedmethods study that analyzed survey data from 834 IoT users in the U.S. Many of our participants treated these devices as co-actors for achieving their goals and continued to use them because they had developed a routine or because the devices influenced their social interactions and identity. Participants limited their use of a device when they did not feel in control, when the device failed to understand their intent, or when they did not understand the device's behavior. We also found that excessive information offered by, disappointment due to, and the complexity of the devices led to their abandonment. Lastly, we discuss the implications of our results for understanding technology (non-)use and provide design recommendations.

show abstract

“…В работе [24] метод LDA используется для автоматического вычисления областей интереса на основе метаданных научных публикаций, таких как название, авторы, ключевые слова и абстракт. Темы, извлеченные из документов, изображаются в виде фиксированных вершин, а авторы публикаций, работающие над разными темами в разные моменты времени, изображаются перемещаемыми вершинами.…”

Section: примеры современных инструментовunclassified

Modern trends in visualization of collections of scientific publications

Apanovich¹

2017

Proceedings of 19th Scientific Conference “Scientific Services &Amp; Internet – 2017”

View full text Add to dashboard Cite

Topic Modeling of Document Metadata for Visualizing Collaborations over Time

Cited by 10 publications

References 16 publications

Computer Methods for Thematic Modeling of Textbooks Collection in Natural Language

Computer Methods for Thematic Modeling of Textbooks Collection in Natural Language

An Analysis of (Non-)Use Practices and Decisions of Internet of Things

Modern trends in visualization of collections of scientific publications

Contact Info

Product

Resources

About