Comparative Analysis of Scientific Papers Collections via Topic Modeling and Co-authorship Networks

2019 ◽  
pp. 77-98 ◽  
Author(s):  
Fedor Krasnov ◽  
Alexander Dimentov ◽  
Mikhail Shvartsman
Keyword(s):  
Comparative Analysis ◽  
Topic Modeling ◽  
Scientific Papers

A comparative analysis of crime fiction and crime nonfiction using topic modeling

2018 ◽  
Vol 22 (3) ◽  
pp. 109-134
Author(s):  
JIHYO KIM ◽  
Eon-Suk Ko
Keyword(s):  
Comparative Analysis ◽  
Topic Modeling ◽  
Crime Fiction

scholarly journals Probabilistic Topic Modeling for Comparative Analysis of Document Collections

2020 ◽  
Vol 14 (2) ◽  
pp. 1-27
Author(s):  
Ting Hua ◽  
Chang-Tien Lu ◽  
Jaegul Choo ◽  
Chandan K. Reddy
Keyword(s):  
Comparative Analysis ◽  
Topic Modeling ◽  
Document Collections ◽  
Probabilistic Topic Modeling

scholarly journals A Comparative Analysis of Disaster Research Trends Using Topic Modeling and Network Analysis

2021 ◽  
Vol 21 (5) ◽  
pp. 79-88
Author(s):  
Chae Yeon Han ◽  
Woo Sik Kim ◽  
Dong Keun Yoon
Keyword(s):  
Comparative Analysis ◽  
Risk Perception ◽  
Topic Modeling ◽  
Community Resilience ◽  
Research Trends ◽  
The Other ◽  
Disaster Research ◽  
Engineering Research ◽  
The Past ◽  
And Behavior

This study aims to analyze differences in domestic and international disaster research trends. We first performed topic modeling on 20,477 papers published in three domestic and 12 international journals over the last 21 years (2000-2020) and then visualized the trends. Based on the extracted topics and keywords, we analyzed keyword networks using Gephi. Research in domestic journals mainly revolved around natural disasters like earthquakes, fire, and flooding. In contrast, international journals spotlighted policy-based topics such as disaster governance and community resilience. Meanwhile, globally, building and civil engineering research has shrunk in recent five years (we refer to this as a cold topic). On the other hand, in the past five years, fire and flood research has appeared more frequently in domestic journals, while international journals have presented more articles on community resilience, risk perception, and behavior (we refer to this as a hot topic). Results of this research can provide suggestions about the directions domestic disaster research should develop in the future.

scholarly journals Identification of Topics from Scientific Papers through Topic Modeling

2021 ◽  
Vol 10 (04) ◽  
pp. 541-548
Author(s):  
Denis Luiz Marcello Owa
Keyword(s):  
Topic Modeling ◽  
Scientific Papers

scholarly journals Emerging Research Topic Detection Using Filtered-LDA

AI ◽  
2021 ◽  
Vol 2 (4) ◽  
pp. 578-599
Author(s):  
Fuad Alattar ◽  
Khaled Shaalan
Keyword(s):  
Final Stage ◽  
Topic Modeling ◽  
Latent Dirichlet Allocation ◽  
Research Topic ◽  
Main Topic ◽  
Topic Detection ◽  
Scientific Papers ◽  
Trending Topics ◽  
Emerging Topics ◽  
Dirichlet Allocation

Comparing two sets of documents to identify new topics is useful in many applications, like discovering trending topics from sets of scientific papers, emerging topic detection in microblogs, and interpreting sentiment variations in Twitter. In this paper, the main topic-modeling-based approaches to address this task are examined to identify limitations and necessary enhancements. To overcome these limitations, we introduce two separate frameworks to discover emerging topics through a filtered latent Dirichlet allocation (filtered-LDA) model. The model acts as a filter that identifies old topics from a timestamped set of documents, removes all documents that focus on old topics, and keeps documents that discuss new topics. Filtered-LDA also genuinely reduces the chance of using keywords from old topics to represent emerging topics. The final stage of the filter uses multiple topic visualization formats to improve human interpretability of the filtered topics, and it presents the most-representative document for each topic.

scholarly journals Layer-Assisted Neural Topic Modeling over Document Networks

2021 ◽  
Author(s):  
Yiming Wang ◽  
Ximing Li ◽  
Jihong Ouyang
Keyword(s):  
Text Classification ◽  
Topic Modeling ◽  
Link Prediction ◽  
Topic Model ◽  
Web Pages ◽  
Text Documents ◽  
Text Data ◽  
Generative Process ◽  
Network Links ◽  
Scientific Papers

Neural topic modeling provides a flexible, efficient, and powerful way to extract topic representations from text documents. Unfortunately, most existing models cannot handle the text data with network links, such as web pages with hyperlinks and scientific papers with citations. To resolve this kind of data, we develop a novel neural topic model , namely Layer-Assisted Neural Topic Model (LANTM), which can be interpreted from the perspective of variational auto-encoders. Our major motivation is to enhance the topic representation encoding by not only using text contents, but also the assisted network links. Specifically, LANTM encodes the texts and network links to the topic representations by an augmented network with graph convolutional modules, and decodes them by maximizing the likelihood of the generative process. The neural variational inference is adopted for efficient inference. Experimental results validate that LANTM significantly outperforms the existing models on topic quality, text classification and link prediction..

Sign in / Sign up

Export Citation Format

Share Document