Emerging research topics detection with multiple machine learning models

Xu, Shuo; Hao, Liyuan; An, Xueli; Yang, Guancan; Wang, Feifei

doi:10.1016/j.joi.2019.100983

Cited by 50 publications

(25 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Following the introduction of NLP techniques, scholars extracted indicators from the text of patents and publications, using a variety of algorithms (Xu et al 2019; see Lee et al 2018 andHassan et al 2018 for comparative analyses) and adopted several similarity measures (Kreutz, Sahitaj, and Schenkel 2020) to delineate the fields and track the emergence and growth of words in documents. As an example, technical keywords may be extracted automatically from the fulltext of patents, their frequency measured using Term Frequency-Inverted Document Frequency metrics, their meaning disambiguated using general lexicons such as WordNet (Joung and Kim 2017).…”

Section: The Text-mining Approach To Emerging Technologiesmentioning

confidence: 99%

Value creation in emerging technologies through text mining: the case of blockchain

Chiarello

Belingheri

Bonaccorsi

et al. 2021

Technology Analysis & Strategic Management

View full text Add to dashboard Cite

As technology progresses, organisations must understand where to direct their value-creating efforts to achieve or sustain competitive advantage. This is even more true in the case of emerging technologies, where innovative activities often focus on achieving a technology promise while overlooking a set of technological, operational, organisational and user-related problems that must be overcome before the technology can fulfil this promise. Through an innovative application of textmining, this paper develops a practical methodology to identify a range of problems related to a technological field in an unsupervised manner, that may benefit firms, researchers and policymakers. We apply the methodology to the field of blockchain and compare it to traditional literature reviews.

show abstract

Section: The Text-mining Approach To Emerging Technologiesmentioning

confidence: 99%

Value creation in emerging technologies through text mining: the case of blockchain

Chiarello

Belingheri

Bonaccorsi

et al. 2021

Technology Analysis & Strategic Management

View full text Add to dashboard Cite

show abstract

“…Research topic detection is important to both veteran and novel researchers, and it helps them recognize and capture the state of the arts and hot topics in a research area (Fang et al , 2018). In addition, research topic detection may also help research foundations and government bodies in policy making, grants approval and innovation management (Xu et al , 2019). Research topic detection was performed based on human judgment and qualitative methods as shown in review articles in a wide range of areas such as life science (Welfare et al , 2006), agriculture (Arno et al , 2009), economics (Cushing, 1989) and information science (Garcia et al , 2019).…”

Section: Introductionmentioning

confidence: 99%

“…Topic modeling includes several types of techniques such as Latent Semantic Indexing (LSI), probabilistic latent semantic analysis (pLSA) and latent Dirichlet allocation (LDA) (Li and Lei, 2019). These techniques have been applied in a wide range of areas such as biology (Kang et al , 2019; Xu et al , 2019), information science (Figuerola et al , 2017), transportation (Kuhn, 2018) and accounting (Fang et al , 2018). Topic modeling is highly efficient in the processing of a large dataset and is able to discover hidden topics.…”

Section: Introductionmentioning

confidence: 99%

“…It should be noted that Xu et al (2019) not only applied topic modeling to extract research topics, but also used machine learning algorithms to determine if a research topic is an emerging one. Their approach provides important implications for the present study.…”

Section: Introductionmentioning

confidence: 99%

“…Their approach provides important implications for the present study. That is, it would be of interest to explore if machine learning methods could predict whether a noun phrase is a research topic, given that such methods were able to achieve satisfactory performance in predicting emerging topics (Xu et al , 2019).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A dependency-based machine learning approach to the identification of research topics: a case in COVID-19 studies

Zhu

Lei

2021

LHT

View full text Add to dashboard Cite

PurposePrevious research concerning automatic extraction of research topics mostly used rule-based or topic modeling methods, which were challenged due to the limited rules, the interpretability issue and the heavy dependence on human judgment. This study aims to address these issues with the proposal of a new method that integrates machine learning models with linguistic features for the identification of research topics.Design/methodology/approachFirst, dependency relations were used to extract noun phrases from research article texts. Second, the extracted noun phrases were classified into topics and non-topics via machine learning models and linguistic and bibliometric features. Lastly, a trend analysis was performed to identify hot research topics, i.e. topics with increasing popularity.FindingsThe new method was experimented on a large dataset of COVID-19 research articles and achieved satisfactory results in terms of f-measures, accuracy and AUC values. Hot topics of COVID-19 research were also detected based on the classification results.Originality/valueThis study demonstrates that information retrieval methods can help researchers gain a better understanding of the latest trends in both COVID-19 and other research areas. The findings are significant to both researchers and policymakers.

show abstract

A scientific research topic trend prediction model based on multi‐LSTM and graph convolutional network

Xue

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

In recent years, with the increase of social investment in scientific research, the number of research results in various fields has increased significantly. Accurately and effectively predicting the trends of future research topics can help researchers discover future research hotspots.However, due to the increasingly close correlation between various research themes, there is a certain dependency relationship between a large number of research themes. Viewing a single research theme in isolation and using traditional sequence problem processing methods cannot effectively explore the spatial dependencies between these research themes. To simultaneously capture the spatial dependencies and temporal changes between research topics, we propose a deep neural network-based research topic hotness prediction algorithm, a spatiotemporal convolutional network model. Our model combines a graph convolutional neural network (GCN) and Temporal Convolutional Network (TCN), specifically, GCNs are used to learn the spatial dependencies of research topics a and use space dependence to strengthen spatial characteristics. TCN is used to learn the dynamics of research topics' trends. Optimization is based on the calculation of weighted losses based on time distance. Compared with the current mainstream sequence prediction models and similar spatiotemporal models on the paper datasets, experiments show that, in research topic prediction tasks, our model can effectively capture spatiotemporal relationships and the predictions outperform state-of-art baselines.

show abstract

Emerging research topics detection with multiple machine learning models

Cited by 50 publications

References 48 publications

Value creation in emerging technologies through text mining: the case of blockchain

Value creation in emerging technologies through text mining: the case of blockchain

A dependency-based machine learning approach to the identification of research topics: a case in COVID-19 studies

A scientific research topic trend prediction model based on multi‐LSTM and graph convolutional network

Contact Info

Product

Resources

About