A novel method to identify emerging technologies using a semi-supervised topic clustering model: a case of 3D printing industry

Zhou, Yuan; Lin, Hui; Liu, Yuanyuan; Ding, Wei

doi:10.1007/s11192-019-03126-8

Cited by 25 publications

(13 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a powerful presentation of technological development, the technology evolutionary path can track historical development, explore knowledge diffusion, and predict future technological trends [49][50][51][52]. The technology evolutionary path describes the emergence, transition, and demise of technologies, helping technical managers and related researchers to understand the process and the current state of technological development, in order to identify and locate major technologies and technical priorities quickly [53][54][55][56][57][58][59][60][61][62].…”

Section: Technology Evolutionary Pathmentioning

confidence: 99%

Unveiling Evolutionary Path of Nanogenerator Technology: A Novel Method Based on Sentence-BERT

et al. 2022

Self Cite

View full text Add to dashboard Cite

In recent years, nanogenerator technology has developed rapidly with the rise of cloud computing, artificial intelligence, and other fields. Therefore, the quick identification of the evolutionary path of nanogenerator technology from a large amount of data attracts much attention. It is of great significance in grasping technical trends and analyzing technical areas of interest. However, there are some limitations in previous studies. On the one hand, previous research on technological evolution has generally utilized bibliometrics, patent analysis, and citations between patents and papers, ignoring the rich semantic information contained therein; on the other hand, its evolution analysis perspective is single, and it is difficult to obtain accurate results. Therefore, this paper proposes a new framework based on the methods of Sentence-BERT and phrase mining, using multi-source data, such as papers and patents, to unveil the evolutionary path of nanogenerator technology. Firstly, using text vectorization, clustering algorithms, and the phrase mining method, current technical themes of significant interest to researchers can be obtained. Next, this paper correlates the multi-source fusion themes through semantic similarity calculation and demonstrates the multi-dimensional technology evolutionary path by using the “theme river map”. Finally, this paper presents an evolution analysis from the perspective of frontier research and technology research, so as to discover the development focus of nanogenerators and predict the future application prospects of nanogenerator technology.

show abstract

Section: Technology Evolutionary Pathmentioning

confidence: 99%

Unveiling Evolutionary Path of Nanogenerator Technology: A Novel Method Based on Sentence-BERT

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…With the gradual standardization of China's land transfer procedures, the industrial planning process is also being scientifically improved. The market-oriented industrial land transfer principle is the best embodiment of the resource allocation theory, such as the development of three-dimensional printing (3D) industry [35] and intelligent manufacturing industry [36].…”

Section: Driving Forces Of Structural Differences In Industrial Land ...mentioning

confidence: 99%

Analysis of Spatial–Temporal Characteristics of Industrial Land Supply Scale in Relation to Industrial Structure in China

Dai

Sheng

Miao

et al. 2021

Land

Self Cite

View full text Add to dashboard Cite

Taking China’s industrial land transfer data as the data source, this study quantitatively analyzes the transfer structure and spatial distribution of China’s industrial land from 2010 to 2019. By constructing the information entropy and the equilibrium degree model of industrial land-use structure, this study evaluates the transfer characteristics of industrial land of different functional types in various provinces of China, analyzes the scale advantages of various types of transferred industrial land by using the land transfer scale advantage index, and summarizes the spatial distribution characteristics of different types of industrial land transfer in China through the spatial center of gravity analysis and cold/hot spot regional distribution mapping. The following results were obtained. (1) There are significant differences in the transfer scale of industrial land among provinces in China. The transfer scale of Eastern and Central China is large, whereas that of Western China is small. (2) From the perspective of land-use structure, the transfer scale of industrial land in the central and western regions is more balanced than that in the east. (3) From the gravity center distribution of the standard deviation ellipse, the land transfer direction of the energy industry, and the mining industry, and other types of industries is more significant than that of the culture and sports hygiene industries, modern manufacturing industry, and high-tech industry. (4) From the analysis of cold and hot spots, the mining industry, the energy industry, and other types of industries in the western region with rich mineral resources are the hot spots of industrial land transfer, and the southeast coast is the cold spot; the eastern coastal area is a hot area for land transfer of modern manufacturing, the high-tech industry, and the culture and sports hygiene industries. The results reveal the regional differences and spatial distribution characteristics of industrial transfer in China and provide a reference for authorities to formulate industrial planning and industrial land collection, storage, and transfer plans.

show abstract

“…A way of detection of the topics within fields of science is to extract topics from textual data, using either topic modeling approaches (Jelodar et al, 2019;Xu, Zhai, et al, 2019;Zhou et al, 2019) or clustering approaches (Curiskis et al, 2020;Kim et al, 2020;Radu et al, 2020;. The overall process, considering the clustering approach in this study can be simplified and put into stages including Document Embedding, Document categorization and clustering, and Labeling of the categories, illustrated in Figure 1.…”

Section: Review Of Topic Detection Processes and Approachesmentioning

confidence: 99%

“…These methods provide ways to categorize, annotate, and understand large volumes of user-generated data (Curiskis et al, 2020). Topic modeling methods, specifically the methods derived from LDA, have been used in many recent and past studies for scientific document analysis, including Xu, Zhai, et al, 2019;Zhou et al, 2019;Xu et al, 2020). An advantage of these approaches is that they do not require the text to be embedded into vectors,as they pursue to find statistical relationships among documents, topics and the terms.…”

Section: Topic Modelingmentioning

confidence: 99%

Embedding-based Detection and Extraction of Research Topics from Academic Documents Using Deep Clustering

Vahidnia

Abbasi

Abbass

2021

Journal of Data and Information Science

View full text Add to dashboard Cite

Purpose Detection of research fields or topics and understanding the dynamics help the scientific community in their decisions regarding the establishment of scientific fields. This also helps in having a better collaboration with governments and businesses. This study aims to investigate the development of research fields over time, translating it into a topic detection problem. Design/methodology/approach To achieve the objectives, we propose a modified deep clustering method to detect research trends from the abstracts and titles of academic documents. Document embedding approaches are utilized to transform documents into vector-based representations. The proposed method is evaluated by comparing it with a combination of different embedding and clustering approaches and the classical topic modeling algorithms (i.e. LDA) against a benchmark dataset. A case study is also conducted exploring the evolution of Artificial Intelligence (AI) detecting the research topics or sub-fields in related AI publications. Findings Evaluating the performance of the proposed method using clustering performance indicators reflects that our proposed method outperforms similar approaches against the benchmark dataset. Using the proposed method, we also show how the topics have evolved in the period of the recent 30 years, taking advantage of a keyword extraction method for cluster tagging and labeling, demonstrating the context of the topics. Research limitations We noticed that it is not possible to generalize one solution for all downstream tasks. Hence, it is required to fine-tune or optimize the solutions for each task and even datasets. In addition, interpretation of cluster labels can be subjective and vary based on the readers’ opinions. It is also very difficult to evaluate the labeling techniques, rendering the explanation of the clusters further limited. Practical implications As demonstrated in the case study, we show that in a real-world example, how the proposed method would enable the researchers and reviewers of the academic research to detect, summarize, analyze, and visualize research topics from decades of academic documents. This helps the scientific community and all related organizations in fast and effective analysis of the fields, by establishing and explaining the topics. Originality/value In this study, we introduce a modified and tuned deep embedding clustering coupled with Doc2Vec representations for topic extraction. We also use a concept extraction method as a labeling approach in this study. The effectiveness of the method has been evaluated in a case study of AI publications, where we analyze the AI topics during the past three decades.

show abstract

A novel method to identify emerging technologies using a semi-supervised topic clustering model: a case of 3D printing industry

Cited by 25 publications

References 49 publications

Unveiling Evolutionary Path of Nanogenerator Technology: A Novel Method Based on Sentence-BERT

Unveiling Evolutionary Path of Nanogenerator Technology: A Novel Method Based on Sentence-BERT

Analysis of Spatial–Temporal Characteristics of Industrial Land Supply Scale in Relation to Industrial Structure in China

Embedding-based Detection and Extraction of Research Topics from Academic Documents Using Deep Clustering

Contact Info

Product

Resources

About