Analyzing the topic distribution and evolution of foreign relations from parliamentary debates: A framework and case study

Lu, Wei; Wang, Jiamin; Hu, Jiming

doi:10.1016/j.ipm.2019.102191

Cited by 11 publications

(8 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen et al ( 2019 ) proposed a nonparametric model (NPMM) that exploits auxiliary word embeddings of NLP to automatically determine whether a given document belongs to existing topics and then inferred the topic number. Additionally, Wei et al ( 2020 ) discovered topics by detecting distinct communities from a co-word network, where words from a specific community belong to the same and unique topic. However, a word usually corresponds to multiple topics in the real word.…”

Section: Related Workmentioning

confidence: 99%

“…Collon et al ( 1991 ) proposed the concepts of centrality and density to characterize research themes based on co-word analysis. Liu et al ( 2017 ) and Wei et al ( 2020 ) used density and centrality to measure the status of research topics in the carbon nanotubes area and the status of communities in the co-word network respectively. The above studies calculate density and centrality of a topic only based on the co-occurrence relationship of feature words within the topic and between different topics.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Evolution analysis of online topics based on ‘word-topic’ coupling network

Zhu

Qin

et al. 2022

Scientometrics

View full text Add to dashboard Cite

Analyzing topic evolution is an effective way to monitor the overview of topic spreading. Existing methods have focused either on the intensity evolution of topics along a timeline or the topic evolution path of technical literature. In this paper, we aim to study topic evolution from a micro perspective, which not only captures the topic timeline but also reveals the topic status and the directed evolutionary path among topics. Firstly, we construct a word network by co-occurrence relationship between feature words. Secondly, Latent Dirichlet allocation (LDA) model is used to automatically extract topics and capture the mapping relationship between words and topics, and then a ‘word-topic’ coupling network is built. Thirdly, based on the ‘word-topic’ coupling network, we describe the topic intensity evolution over time and measure topic status considering the contribution of feature words to a topic. The concept of topic drifting probability is proposed to identify the evolutionary path. Experimental results conducted on two real-world data sets of “COVID-19” demonstrate the effectiveness of our proposed method.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Evolution analysis of online topics based on ‘word-topic’ coupling network

Zhu

Qin

et al. 2022

Scientometrics

View full text Add to dashboard Cite

show abstract

“…Navarretta and Hansen (2020) analyze the words used in the Danish parliament to determine if speakers of the four parties can be detected using machine learning models. Wei, Jiamin, and Jiming (2020) analyze foreign relations based on parliamentary texts. First, topic words are extracted from parliamentary texts, and then a co-word network is constructed to represent the correlation structure of topic words.…”

Section: National Parliamentsmentioning

confidence: 99%

Multi-aspect Multilingual and Cross-lingual Parliamentary Speech Analysis

Miok¹,

Tenorio²,

Osenova³

et al. 2022

Preprint

View full text Add to dashboard Cite

Parliamentary and legislative debate transcripts provide an exciting insight into elected politicians' opinions, positions, and policy preferences. They are interesting for political and social sciences as well as linguistics and natural language processing (NLP). Exiting research covers discussions within individual parliaments. In contrast, we apply advanced NLP methods to a joint and comparative analysis of six national parliaments (Bulgarian, Czech, French, Slovene, Spanish, and United Kingdom) between 2017 and 2020, whose transcripts are a part of the ParlaMint dataset collection. Using a uniform methodology, we analyze topics discussed, emotions, and sentiment. We assess if the age, gender, and political orientation of speakers can be detected from speeches. The results show some commonalities and many surprising differences among the analyzed countries.

show abstract

“…For example, during an emergency response, the information disseminated on social networks may contain rumors, false or true but outdated information (Zhao et al, 2014), and emergency managers can use rumor detection mechanisms to help them identify false information. Some studies focus on the classification and evolution of social media text topics, such as the application of document clustering and topic modeling techniques to classify, annotate, and understand the content generated by a large number of users (Curiskis, Drake, Osborn, & Kennedy, 2020), and the evolution of the theme of the event can be sorted out by building a co-word network (Wei et al, 2020). However, the information flow in social media is very large in the process of collecting relevant data.…”

Section: Thematic Analysis Of Social Media In Emergencymentioning

confidence: 99%

Visualization of Emergency Needs Posted on Social Media by Metaphor Map

Cui

et al. 2021

Data and Information Management

View full text Add to dashboard Cite

Thematic analysis based on a social network is one of the effective means in emergency management. To improve users’ understanding, the results of the thematic analysis are often displayed through visualization. However, the previous researches on text theme visualization rarely considered the unified representation of theme structure and theme evolution. Cognitive load leads to difficulty, and it happens due to the separate representation of structure and evolution relationship and it still increases because of the characteristics of urgency, uncertainty, etc. Therefore, a metaphor map is introduced in this study to overcome the limits of previous visualization tools in characterizing the structure and evolutionary relationship of emergency. On the one hand, different elements in the metaphor map represent the information of popularity and structure of the demand, respectively. On the other hand, the visual design based on the metaphor map strengthens the representation of the content and evolution states of the demand themes. At the theoretical level, a visualization method for emergency needs based on the metaphor map is proposed in this study, which enriches the theory of emergency information visualization. At the practical level, this study explores the design of a visualization system based on the metaphor map under crisis scenarios, which enhances the interaction between users and crisis information, and provides references for decision-making such as emergency material scheduling and emergency resource coordination.

show abstract

Analyzing the topic distribution and evolution of foreign relations from parliamentary debates: A framework and case study

Cited by 11 publications

References 37 publications

Evolution analysis of online topics based on ‘word-topic’ coupling network

Evolution analysis of online topics based on ‘word-topic’ coupling network

Multi-aspect Multilingual and Cross-lingual Parliamentary Speech Analysis

Visualization of Emergency Needs Posted on Social Media by Metaphor Map

Contact Info

Product

Resources

About