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

Ma, Jian; Wang, Lei; Zhang, Yuan-Rong; Wang, Yuan; Guo, Wei

doi:10.1016/j.eswa.2022.118695

Cited by 28 publications

(10 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this study, we perform semantic relevance visualization analysis of textual information, using two methods, Word2Vec and TF-IDF, respectively. Word2Vec learns the vector representations of words in a high-dimensional vector space and calculates the cosine distances between words to show their relevance 26 . First, the text words are converted to 100-dimensional word vectors using Word2Vec, and then the high-dimensional vectors are reduced to 2 dimensions by PCA and finally plotted as a 2D image.…”

Section: Methodsmentioning

confidence: 99%

ITFNet-API: Image and Text Based Multi-Scale Cross-Modal Feature Fusion Network for Agricultural Pest Identification

Yu,

Xu,

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

In agricultural production, pest problems are inevitable. In recent years, China has suffered annual losses of up to 40 million tons of grain due to various pests and diseases. There are over one million known insect species in the natural world, exhibiting complex and diverse morphologies, making manual identification costly. With the advancement of deep learning technologies, methods relying solely on image data for crop pest identification have achieved some success. However, these methods heavily depend on numerous high-quality annotated images. Many existing approaches overlook the role and value of other modalities beyond images and rely solely on low-level image features for recognition. They fail to fully exploit semantic correlations between multimodal data, leading to poor reliability and interpretability of the recognition results. Moreover, in real-world scenarios, pest habitats are complex and diverse, with varying scales, imposing high demands on the practical application of models. To address these challenges, this paper proposes a Multi-Scale Cross-Modal Feature Fusion Model (ITFNet-API) utilizing multi-scale visual features and textual features for cross-modal attention learning. Super-resolution reconstruction techniques are introduced to restore high-frequency information in low-quality images. To avoid altering low-frequency information during the reconstruction process, the reconstructed high-quality images are combined with the original images and fed into the model for feature learning to enrich pest features. The proposed Image and Text Fusion Module (ITFM) performs multi-scale cross-modal information fusion and an Inverse Transpose Convolution (ITC) network module is introduced to restore multi-scale visual features. The obtained visual features are input into the neck and head networks of the YOLOv4 (You Only Look Once version 4) model to obtain pest category and location information in each image. Finally, to verify the model’s practical application capability, this paper introduces an Arbitrary Combination Image Enhancement (ACIE) data augmentation method which generates a batch of complex multi-target, multi-scale pest images in challenging scenarios for data augmentation and model training. We conducted extensive comparative experiments based on the IP102 dataset to validate the effectiveness of the proposed method. The experimental results indicate that our method achieved an accuracy rate of 82.15% in pest recognition, outperforming other advanced methods significantly with an AP50 of 92.18%. Moreover, in multi-target recognition,the accuracy rate reached 45.24% with an AP50 of 43.04%.

show abstract

Section: Methodsmentioning

confidence: 99%

ITFNet-API: Image and Text Based Multi-Scale Cross-Modal Feature Fusion Network for Agricultural Pest Identification

Yu,

Xu,

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Firstly, the Word2Vec model is conducted to construct the word vector space of paper and patent data. As a word vector tool, the Word2Vec model can not only map words from highdimensional space to low-dimensional space, but also retain the existing position between word vectors to solve the problem of vector sparseness and semantic connection (Ma et al, 2023). Secondly, the cosine similarity between the vectors corresponding to the high-value paper topics and the patent topics is calculated to obtain the topic similarity matrix.…”

Section: Selecting Patent Topicsmentioning

confidence: 99%

Technology opportunity discovery of proton exchange membrane fuel cell from the perspective of papers-patents correlation analysis

Feng

Liu²,

Wang³

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

Papers and patents can respectively present the latest progress of scientific research and technological development. Combining the two for correlation analysis has certain reference significance for technology opportunity discovery. Therefore, this paper proposes a method for technology opportunity discovery of proton exchange membrane fuel cell from the perspective of papers-patents correlation analysis. Firstly, papers and patent data are collected from papers and patent databases and the LDA model is applied to extract paper and patent topics. Secondly, the indicators of topic heat and novelty are calculated to select high-value paper topics. After that, the similarity analysis between high-value paper topics and all patent topics is considered to select the patent topics with development potential. Finally, the patent texts with high relevance to these patent topics with development potential are positioned. The technical keywords in them are extracted by text mining tool and classified into innovation dimensions according to their attributes and the TEMPEST model. After that, the innovation rules in the SCAMPER model are introduced to combine with the technical keywords in each innovation dimension to identify specific technology opportunities. An empirical study on the technology of proton exchange membrane fuel cell provides sufficient evidence of the method’s ability to discover technology opportunities. This paper contributes by generating four specific technology opportunities, which can make up for the existing defects of proton exchange membrane fuel cells and provide useful guidance for companies to carry out technological innovation.

show abstract

“…Thus, Kim et al (2020) used Word2Vec in combination with spherical k-means clustering to reveal the crypto industry trends. Word2Vec was also used by Gao et al (2022) and Ma et al (2023). Amado et al (2018) created dictionaries of words by category in a semiautomated manner and clustered them via a document-term matrix and latent Dirichlet allocation (LDA) algorithm.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Amado et al (2018) created dictionaries of words by category in a semiautomated manner and clustered them via a document-term matrix and latent Dirichlet allocation (LDA) algorithm. Mohammadi and Karami (2022), Porter (2018), Sharma and Sharma (2022), Kukreja (2022) and Ma et al (2023) also used the LDA approach to cluster terms; Te Liew et al (2014) applied the n-gram extraction through the NLTK library and examined the list of top sustainability-related terms based on TF–IDF statistics (TF – term frequency, IDF – inverse document frequency).…”

Section: Literature Reviewmentioning

confidence: 99%

Identifying emerging trends and hot topics through intelligent data mining: the case of clinical psychology and psychotherapy

Sokolova,

Lobanova,

Kuzminov

2023

View full text Add to dashboard Cite

Purpose The purpose of the paper is to present an integrated methodology for identifying trends in a particular subject area based on a combination of advanced text mining and expert methods. The authors aim to test it in an area of clinical psychology and psychotherapy in 2010–2019. Design/methodology/approach The authors demonstrate the way of applying text-mining and the Word2Vec model to identify hot topics (HT) and emerging trends (ET) in clinical psychology and psychotherapy. The analysis of 11.3 million scientific publications in the Microsoft Academic Graph database revealed the most rapidly growing clinical psychology and psychotherapy terms – those with the largest increase in the number of publications reflecting real or potential trends. Findings The proposed approach allows one to identify HT and ET for the six thematic clusters related to mental disorders, symptoms, pharmacology, psychotherapy, treatment techniques and important psychological skills. Practical implications The developed methodology allows one to see the broad picture of the most dynamic research areas in the field of clinical psychology and psychotherapy in 2010–2019. For clinicians, who are often overwhelmed by practical work, this map of the current research can help identify the areas worthy of further attention to improve the effectiveness of their clinical work. This methodology might be applied for the identification of trends in any other subject area by taking into account its specificity. Originality/value The paper demonstrates the value of the advanced text-mining approach for understanding trends in a subject area. To the best of the authors’ knowledge, for the first time, text-mining and the Word2Vec model have been applied to identifying trends in the field of clinical psychology and psychotherapy.

show abstract

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

Cited by 28 publications

References 32 publications

ITFNet-API: Image and Text Based Multi-Scale Cross-Modal Feature Fusion Network for Agricultural Pest Identification

ITFNet-API: Image and Text Based Multi-Scale Cross-Modal Feature Fusion Network for Agricultural Pest Identification

Technology opportunity discovery of proton exchange membrane fuel cell from the perspective of papers-patents correlation analysis

Identifying emerging trends and hot topics through intelligent data mining: the case of clinical psychology and psychotherapy

Contact Info

Product

Resources

About