Topic Evolution Analysis Research Articles

Research on "The Belt and Road Initiative" report of think tank based on theme evolution and identification--Taking 2013-2020 as an example.

China's "the Belt and Road Initiative" (BRI) is a top-level cooperation initiative among countries proposed by China, which has promoted China's cooperation with relevant countries in various aspects and fields. Research reports from think tanks and experts on the evaluation, analysis, and research conclusions of the BRI can reflect the stance, opinions, and demands of various countries abroad regarding the initiative. This paper takes the BRI reports of important think tanks in the " Global Go To Think Tank Index Report 2020" as the subject of its research, and analyzes the key points and development trends of foreign think tank research on the BRI by using text mining, topic evolution, and social network analysis. It provides reasonable suggestions and ideas for promoting the construction of the BRI and deepening related cooperation in China. Research shows that the thematic distribution of research reports on the BRI by think tanks is mainly focused on the fields of politics, economy, and military. The research areas are relatively stable, and there is not a strong trend of thematic evolution. The evolution paths are also mainly distributed in the fields of politics, economy, and military. There are not many expansions in the thematic evolution directions over the years, and there is a strong inheritance of themes. The connection between research themes and the main purpose of the BRI is somewhat inadequate, indicating a certain limitation in the understanding of the BRI.

Core Technology Topic Identification and Evolution Analysis Based on Patent Text Mining—A Case Study of Unmanned Ship

Accurate identification and evolutionary analysis of core technology topics within patent texts play a crucial role in enabling enterprises to discern the development trajectory of core technologies, optimize research and development (R&D) strategies, and foster technological innovation. Based on the perspective of time series dynamic analysis, this study uses the Latent Dirichlet Allocation (LDA) topic modeling and TF-IDF text vectorization methods to comprehensively mine and identify patent technology topics in the field of unmanned ships. This study deeply analyzes the dynamic evolution of unmanned ship technology topics from two aspects: the evolution of technology theme intensity and the evolution of technology theme content. We refine the development characteristics and future development directions of unmanned ship technology. The findings reveal two hot technologies, six growth technologies, and six declining technologies in unmanned ship technology. Furthermore, the analysis of technical topic evolution illustrates a pattern of fragmentation, inheritance, and integration. This study advances the methodologies used for identifying and analyzing patent technology topics and helps to grasp the development rules and evolutionary trends of core technologies. In addition, this paper has reference value for the research and practice of core technology topic identification and evolution analysis methods based on patent text mining.

Multilingual topic evolution and comparative analysis for electronic commerce research: A combination of BERTopic and SBERT

Electronic commerce (EC) has become the most critical business activity in the world. China has become the world’s largest market for EC. Over the past three decades, numerous researches have examined the current status of the development of monolingual EC research in specific scenarios. However, the paradigm shift in EC development through the analysis of the dynamic evolution of semantic information has not yet been examined, and the distinctions and connections between multilingual EC studies have not yet been established. This study analyzed 16,207 English and 17,850 Chinese EC-related articles from the Web of Science database and CNKI by combining the BERTopic topic model and SBERT sentence embedding-based similarity computations. The results reveal the distributions of global and local topics in the English and Chinese EC literature, analyze the semantic intricacies of topic convergence and evolution across continuous time, as well as the distinctions and connections between English and Chinese topics. Finally, the evolutionary patterns and life cycle of three crucial English and Chinese topics are explored respectively, including their emergence, development, maturity, and decline. Overall, this study provides a comprehensive overview of EC studies from a topic perspective.

Netizens' concerns during COVID-19: a topic evolution analysis of Chinese social media platforms

PurposeThis study analyzes the evolution of topics related to COVID-19 on Chinese social media platforms with the aim of identifying changes in netizens' concerns during the different stages of the pandemic.Design/methodology/approachIn total, 793,947 posts were collected from Zhihu, a Chinese Question and Answer website, and Dingxiangyuan, a Chinese online healthcare community, from 31 December, 2019, to 4 August, 2021. Topics were extracted during the prodromal and outbreak stages, and in the abatement–resurgence cycle.FindingsNetizens' concerns varied in different stages. During the prodromal and outbreak stages, netizens showed greater concern about COVID-19 news, the impact of COVID-19 and the prevention and control of COVID-19. During the first round of the abatement and resurgence stage, netizens remained concerned about COVID-19 news and the prevention and control of the pandemic, however, less attention was paid to the impact of COVID-19. During later stages, popularity grew in topics concerning the impact of COVID-19, while netizens engaged more in discussions about international events and the raising of spirits to fight the global pandemic.Practical implicationsThis study contributes to the practice by providing a way for the government and policy makers to retrospect the pandemic and thereby make a good preparation to take proper measures to communicate with citizens and address their demands in similar situations in the future.Originality/valueThis study contributes to the literature by applying an adapted version of Fink's (1986) crisis life cycle to create a five-stage evolution model to understand the repeated resurgence of COVID-19 in Mainland China.

Advancements in Rumor Detection Research Based on Bibliometrics and S-curve Technology Evolution Theory

With the rapid development of social media, new opportunities have been provided for the generation and dissemination of online rumors, making systematic study of rumor detection of great significance for the control and governance of internet rumors. Addressing the limitations of past review studies on rumor detection which were characterized by a single perspective, reliance on subjective judgment, and lack of technological evolution theory, this paper reviews 983 rumor detection articles in the SCI-EXPANDED, SSCI, CPCI-S, CPCI-SSH, CCR-EXPANDED, and IC databases of the Web of Science. Utilizing Citespace and VOSviewer for visual analysis of the articles, and adopting bibliometric theories like network analysis and topic evolution analysis, this study identifies core research groups in the field of rumor detection based on author collaboration network and institution collaboration network. Through high-frequency keyword clustering graph and keyword co-occurrence graph, the study unveils topic associations and cluster structures among keywords, explicates research hotspots in the field of rumor detection, and conducts a fine-grained critical comparative analysis. According to keyword time graph, keyword bursts table, and trends in the number of publications in hot technology fields, combined with the S-curve technology evolution theory, the study discerns the life cycle and research trends of technologies in the rumor detection field. Compared to existing literature reviews, this paper is the first to propose integrating bibliometrics and S-curve technology evolution theory to reveal the state of relevant technologies and research frontiers.

Analysis of Topic Evolution in Educational Data

Analyzing the developing trends of educational data has always been an important issue. However, it is challenging to do it manually because of the data expansion in recent years. A topic evolution-analyzing framework, comprised of a data crawling module and a topic-processing module, is proposed to solve this problem. The Chongqing Three Gorges Medical College of China was used as a case for the experiment, and the framework was implemented using Python language. First, the data were obtained from the website, and its format was reorganized, which is appropriate to be fed into the topic-processing module. Subsequently, all topics were obtained and interpreted as several related phrases. Finally, the topic evolution was obtained over years and months. This work can help education organizations with their historical information summarization, contributing to their development planning and providing academic support to the decision-makers.

Research on Topic Evolution Path Recognition Based on LDA2vec Symmetry Model

Topic extraction and evolution analysis became a research hotspot in the academic community due to its ability to reveal the development trend of a certain field and discover the evolution law of topic content in different development stages of the field. However, current research methods still face challenges, such as inaccurate topic recognition and unclear evolution paths, which can seriously compromise the comprehensiveness and accuracy of the analysis. To address the problem, the paper proposes a topic evolution path recognition method based on the LDA2vec symmetry model. Under given conditions, both the LDA and Word2vec used in the model conform to the structural symmetry of their datasets in high-dimensional space, and the fused LDA2vec method improves the accuracy of the analysis results. Firstly, we recognize the topics based on the LDA model, which uses Gibbs symmetric sampling and obeys the symmetric Dirichlet distribution to ensure data convergence. Secondly, Word2vec is used to learn the contextual information of the topic words in the document collection, and the words in the corpus are projected as vectors in the high-dimensional space so that the computed pairs of words with similar semantics have symmetry in the hyperplane of the high-dimensional space. Subsequently, the word vector is used as a weight, and the LDA topic word probability value is weighted to generate a new topic vector. Thirdly, the vector similarity index is employed to calculate the semantic similarity among topics at adjacent stages, and evolution paths that directly reflect the topic relationships are constructed. Finally, an empirical study is conducted in the field of data security to demonstrate the effectiveness of the proposed approach for topic evolution analysis. The results show that the proposed approach can accurately recognize the topic content and construct clear evolution paths, which contribute to the comprehensive and accurate analysis of topic evolution in a specific research field.

Topic evolution analysis: an exploratory study for the field of mental models

Mental models are an expression of individual cognitive states and have been widely employed to explain and drive innovation in design. However, rarely studies have discussed the topic evolution of mental models itself. With this in mind, this paper proposes a framework integrating Latent Dirichlet Allocation and Word2Vec to mine the topic evolution information of mental models over the past four decades. 4286 abstracts of relevant research papers were collected, and 7 main evolutionary paths of mental models were identified, providing both semantic information and its intercorrelation of topics across the years. This sheds light on the full life cycle of the topic, which includes emerging, developing, maturing, and fading in different time slices. Additionally, each evolutionary path of mental models related to design is also discussed in detail. Based on the above, we mapped the topic's evolution in detail and provided insights to assist researchers in developing a comprehensive understanding of the topic, as well as suggestions for future research.

A Recognition Method of Measuring Literature Topic Evolution Paths Based on K-means-NMF

In this study, we propose a recognition method of measuring literature topic evolution paths based on K-means-NMF in order to address problems such as the unobvious effect of topic clustering, high degree of mixing in clustering results, and unclear topic evolution paths that exist in the current research of topic evolution analysis. Firstly, we enhance the traditional NMF (Nonnegative Matrix Factorization) topic model by combining the K-means clustering algorithm with the NMF model to improve the accuracy of topic clustering and reduce the correlation among topics. Secondly, we perform the topic co-occurrence analysis based on the clustering results to identify important topic categories for recognizing critical evolution paths to solve the problem of multiple possible evolution paths in the experiment. Thirdly, we adopt the Word2Vec model to calculate topic word vectors in a semantic context to improve the accuracy of the correlation strength between topics at adjacent stages. Finally, we adopt the above method to conduct an empirical study using intelligent algorithms as an example. The experimental results show that this research method effectively identifies important topics and topic developments in the subject area, which can support scientific research and science and technology policy development.

MatrixSim: A new method for detecting the evolution paths of research topics

• A new method for detecting the evolution paths of research topics called MatrixSim is proposed. • The community structure of co-word networks is maximally preserved. • The similarity of topic communities in terms of both words and relations is integrated through MatrixSim. • Two sets of experiments are designed to verify the validity and feasibility in research topic evolution analysis. • Methodological support is provided for researchers to conduct prospective research activities. In this study, MatrixSim, a new method for detecting the evolution paths of research topics based on matrix similarity, was proposed. In the analysis of research topic evolution with the help of co-word networks, in contrast to traditional methods of topic evolution path detection, such as cosine similarity and edge similarity, MatrixSim is based on the local community structure of topic communities in co-word networks and considers the similarity of research topics in both nodes and edges, that is, words and inter-word relations. Using the library and information science field as an example, two sets of experiments were designed for topic similarity detection and subject-specific research topic evolution analysis to evaluate and verify the performance of MatrixSim in detecting the evolution paths of research topics and its validity and feasibility in research topic evolution analysis. The results confirm that MatrixSim performs well in detecting the evolution paths of research topics. It can correlate important research topics, help describe the research development process in scientific fields, reveal the internal evolutionary features of research topics, and thus discover and track the research frontiers in scientific fields. This study provides significant methodological support for researchers conducting prospective research activities.

Discovery of topic evolution path and semantic relationship based on patent entity representation

PurposeThis paper aims to propose a method for better discovering topic evolution path and semantic relationship from the perspective of patent entity extraction and semantic representation. On the one hand, this paper identifies entities that have the same semantics but different expressions for accurate topic evolution path discovery. On the other hand, this paper reveals semantic relationships of topic evolution for better understanding what leads to topic evolution.Design/methodology/approachFirstly, a Bi-LSTM-CRF (bidirectional long short-term memory with conditional random field) model is designed for patent entity extraction and a representation learning method is constructed for patent entity representation. Secondly, a method based on knowledge outflow and inflow is proposed for discovering topic evolution path, by identifying and computing semantic common entities among topics. Finally, multiple semantic relationships among patent entities are pre-designed according to a specific domain, and then the semantic relationship among topics is identified through the proportion of different types of semantic relationships belonging to each topic.FindingsIn the field of UAV (unmanned aerial vehicle), this method identifies semantic common entities which have the same semantics but different expressions. In addition, this method better discovers topic evolution paths by comparison with a traditional method. Finally, this method identifies different semantic relationships among topics, which gives a detailed description for understanding and interpretation of topic evolution. These results prove that the proposed method is effective and useful. Simultaneously, this method is a preliminary study and still needs to be further investigated on other datasets using multiple emerging deep learning methods.Originality/valueThis work provides a new perspective for topic evolution analysis by considering semantic representation of patent entities. The authors design a method for discovering topic evolution paths by considering knowledge flow computed by semantic common entities, which can be easily extended to other patent mining-related tasks. This work is the first attempt to reveal semantic relationships among topics for a precise and detailed description of topic evolution.

Topic Classification of Central Bank Monetary Policy Statements: Evidence from Latent Dirichlet Allocation in Lesotho

Abstract This article develops a baseline on how to analyse the statements of monetary policy from Lesotho’s Central Bank using a method of topic classification that utilizes a machine learning algorithm known as Latent Dirichlet Allocation. To evaluate the changes in the policy distribution, the classification of topics is performed on a sample of policy statements spanning from February 2017 to January 2021. The three-topic Latent Dirichlet Allocation model extracted topics that remained prominent throughout the sample period and were most closely reflective of the functions of the Central Bank of Lesotho Monetary Policy Committee. The topics identified are: (i) International Monetary and Financial Market Conditions; (ii) Monetary Policy Committee and International Reserves; (iii) Regional and International Economic Policy Conditions. The three-topic Latent Dirichlet Allocation model was determined as the most appropriate model through which a consistent analysis of topic evolution in Central Bank of Lesotho Monetary Policy Statements can be performed.

An integrated latent Dirichlet allocation and Word2vec method for generating the topic evolution of mental models from global to local

Mental models play a crucial role in explaining and driving human innovation activities. To help researchers clarify the changes of mental models in various innovation situations, an exploration of its topic dynamic evolution changes is urgently needed. However, most existing works have discussed the topic-semantic distributions of collected documents along the overall timeline, which ignores the semantic details of fusion and evolution between topics in continuous time. This paper discovers and reveals the multi-level information evolving of topics, by integrating latent Dirichlet allocation (LDA) and Word2vec harmoniously to generate the topic evolution maps of the corpus from global to local perspectives. Which include topic distribution trends and their dynamic evolution under the overall time series, as well as the merging and splitting of semantic information between topics in the adjacent time span. These reveal the correlation between topics and the full life cycle of a topic emerging, developing, maturing, and fading. Then, the integrated method was used to perform an analysis of topic evolution with 3984 abstracts of mental model-related papers published between 1980 and 2020. Finally, the performance of the proposed method was compared to that of three traditional topic evolution generated methods based on the standard evaluation metrics. The experimental results demonstrated that our method outperforms other methods both in terms of the content and strength of topic evolution. The proposed method could mine the latent evolution information more clearly and comprehensively from a vast number of papers and is also suited to the various applications of expert systems related to information mining works.

Tracing the technological trajectory of coal slurry pipeline transportation technology: An HMM-based topic modeling approach

Coal slurry pipeline transportation is an important way to realize green coal logistics. However, there are still challenges in understanding the cognitive aspects of coal slurry pipeline transportation technology development trajectory. This study attempts to trace and predict the technology trend from patent texts through the stochastic process analysis of topic evolution. It helps understand the challenges in the development process of coal slurry pipeline transportation technology. And capture trends and development characteristics of the technology to improve research and development (R&D) efficiency and sustainability. As a result, this study extracts potential technology topics from patent text by using the Latent Dirichlet Distribution method. Then, a Word2vec-based topic word vector model is applied to calculate the cosine similarity between topics. And the HMM-based topic evolution trend model is constructed by introducing the Hidden Markov Model (HMM) which can portray a dual stochastic process. Finally, it is used to analyze and predict trends in the technological evolution of this field. It was found that the advancement of technology related to pulping is fundamental to promoting the development of coal slurry pipeline transportation technology, which is also a common research topic. Finally, technologies related to pipeline transportation capacity enhancement and the industrial application of coal slurry will be the focus of future R&D in this field with broad research and application prospects. This study is intended to provide directions for sustainable R&D activities in coal slurry pipeline transportation technology, facilitate interdisciplinary discussions, and provide objective data for future decisions making for scientists and R&D managers in this field.

The Performance of Topic Evolution Based on a Feature Maximization Measurement for the Linguistics Domain

Understanding the performance of the data mining approach and topic evolution in a certain scientific domain is imperative to capturing key domain developments and facilitating knowledge transfer within and across domains. Our research selects linguistics as an exploratory domain and exploits the feature maximization (FM) measurement for feature selection, combined with the contrast ratio to conduct the diachronic analysis for the linguistics domain’s topics. To accurately mine the linguistics domain’s topics and obtain the optimal clustering model selection, we exploit an integrated method associated with the deep embedding for clustering (DEC) algorithm based on the keywords-based Text Representation Matrix (KTRM) and Lamirel’s EC index and test the performance of this method. The results show that the FM measurement is applicable in the linguistics domain for topic mining, and the combinatory method has the advantage of an unbiased clustering optimization model and applies to the design of non-parameter clustering and algorithms from the low dimension to the high dimension of datasets. The findings suggest that this approach could be suitable for a diachronic analysis of topic evolution and facilitate the performance of topic detection. In addition, these findings of text detection can rise to knowledge fusion cognition with the factor of language as an available research objective in interdisciplinary research.

Semantic-enhanced topic evolution analysis: a combination of the dynamic topic model and word2vec

Semantic-enhanced topic evolution analysis: a combination of the dynamic topic model and word2vec

The Development History and Research Tendency of Medical Informatics: Topic Evolution Analysis.

BackgroundMedical informatics has attracted the attention of researchers worldwide. It is necessary to understand the development of its research hot spots as well as directions for future research.ObjectiveThe aim of this study is to explore the evolution of medical informatics research topics by analyzing research articles published between 1964 and 2020.MethodsA total of 56,466 publications were collected from 27 representative medical informatics journals indexed by the Web of Science Core Collection. We identified the research stages based on the literature growth curve, extracted research topics using the latent Dirichlet allocation model, and analyzed topic evolution patterns by calculating the cosine similarity between topics from the adjacent stages.ResultsThe following three research stages were identified: early birth, early development, and rapid development. Medical informatics has entered the fast development stage, with literature growing exponentially. Research topics in medical informatics can be classified into the following two categories: data-centered studies and people-centered studies. Medical data analysis has been a research hot spot across all 3 stages, and the integration of emerging technologies into data analysis might be a future hot spot. Researchers have focused more on user needs in the last 2 stages. Another potential hot spot might be how to meet user needs and improve the usability of health tools.ConclusionsOur study provides a comprehensive understanding of research hot spots in medical informatics, as well as evolution patterns among them, which was helpful for researchers to grasp research trends and design their studies.

Cross event detection and topic evolution analysis in cross events for man-made disasters in social media streams

Cross event detection and topic evolution analysis in cross events for man-made disasters in social media streams

Cross event detection and topic evolution analysis in cross events for man-made disasters in social media streams

Cross event detection and topic evolution analysis in cross events for man-made disasters in social media streams

Topic evolution analysis of radar research using a dynamic topic model based on latent Dirichlet allocation

This work applies a dynamic topic model based on latent Dirichlet allocation to investigate the evolution of radar research and applications. To address the problem that processing a large number of papers exceeds the capacity of computers, we propose a method to sample documents according to their citation count. Of 104,428 sampled articles, 108 research topics are extracted. The evolution of topics is analysed from two dimensions: content and strength. The results show that radar technology, which arose mainly from physics and engineering science, has been widely applied in studies in the civil engineering, geographical, environmental, meteorological, geological, agricultural, ecological, among others. In the long-term development of radar, new technologies have continuously been produced. At the individual topic level, the research content has changed over time. The development objectives of radar systems are to enhance functionality, extract more information and improve clarity.