Penalized regression models for patent keyword analysis

Kim, Jong Min; Ryu, Jea bok; Lee, Seung Joo; Jun, Sunghae

doi:10.3233/mas-170398

Cited by 3 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The row and column of this matrix are document and word, respectively, and each element is the frequency value of a word occurring in a patent document. So far, various data analysis methods have been studied for the analysis of document-word matrix [5,32,33]. Kim and Jun built the patent document-word matrix using text mining, and analyzed it by graphical causal inference and copula regression.…”

Section: Related Workmentioning

confidence: 99%

“…Park et al (2017) extracted the text data from patent documents and analyzed the matrix data using fuzzy learning algorithms [20]. Kim et al (2017) selected the keywords from patent data and used the penalized regression models for a patent keyword analysis [33]. Park and Jun (2020) analyzed patent keyword data using a technological cognitive diagnosis model [21].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Zero-Inflated Patent Data Analysis Using Compound Poisson Models

Park

Jun

2023

Applied Sciences

View full text Add to dashboard Cite

A large part of big data consists of text documents such as papers, patents or articles. To analyze text data, we have to preprocess the text documents and build a structured data based on a document-word matrix using various text mining techniques. This is because statistics and machine learning algorithms used in text analysis require structured train data. The row and column of the matrix are document and word, respectively. The element of the matrix represents the frequency value of the word occurring in each document. In general, because the number of words is much larger than the number of documents, most elements have zero values. Due to the sparsity problem caused by inflated zeros, the performance of the predictive model has decreased. In this paper, we propose a method to solve the sparsity problem and improve the model performance in text data analysis. We perform compound Poisson linear modeling to make the proposed method. To show the performance of our proposed method, we collect and analyze the patent documents from patent databases. In our experimental results, we compared the value of the Akaike information criterion (AIC) of the proposed model with traditional models, such as linear model, generalized linear model and zero-inflated Poisson model. Additionally, we illustrated that the AIC value of our proposed model is smaller than others. Therefore, we verify the validity of this paper.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Zero-Inflated Patent Data Analysis Using Compound Poisson Models

Park

Jun

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In addition, many patent analysis studies using visualization have been published in various fields [2,[4][5][6]. In addition to this network visualization technique, performed patent analysis using statistical methods [7]. They considered penalized regression models based on ridge and least absolute shrinkage and selection operator (LASSO) regressions to get patent analysis results.…”

Section: Introductionmentioning

confidence: 99%

Patent Keyword Analysis Using Time Series and Copula Models

et al. 2019

View full text Add to dashboard Cite

The technological keywords extracted from patent documents have much information about a developed technology. We can understand the technological structure of a product by examining the results of patent analysis. So far, much research has been done on patent data analysis. The technological keywords of patent documents contain representative information on the developed technology. As such, the patent keyword is one of the most important factors in patent data analysis. In this paper, we propose a patent data analysis model combining a integer valued time series model and copula direction dependence for integer valued patent keyword analysis over time. Most patent keywords are frequency values and keywords often change over time. However, the existing patent keywords analysis works do not account for two major factors: integer value and time. For modeling integer valued keyword data with time factor, we use a copula directional dependence model based on marginal regression with a beta logit function and integer valued generalized autoregressive conditional heteroskedasticity model. Using the proposed model, we find technological trends and relations in the target technological domain. To illustrate the performance and implication of our paper, we carry out experiments using the patent documents applied and registered by Apple company. This study contributes to the effective planning for the research and development of technologies by utilizing the evolution of technology over time.

show abstract

Proposing Robust LAD-Atan Penalty of Regression Model Estimation for High Dimensional Data

Yousef

Ali

2020

Baghdad Sci.J

View full text Add to dashboard Cite

The issue of penalized regression model has received considerable critical attention to variable selection. It plays an essential role in dealing with high dimensional data. Arctangent denoted by the Atan penalty has been used in both estimation and variable selection as an efficient method recently. However, the Atan penalty is very sensitive to outliers in response to variables or heavy-tailed error distribution. While the least absolute deviation is a good method to get robustness in regression estimation. The specific objective of this research is to propose a robust Atan estimator from combining these two ideas at once. Simulation experiments and real data applications show that the proposed LAD-Atan estimator has superior performance compared with other estimators.

show abstract

Penalized regression models for patent keyword analysis

Cited by 3 publications

References 12 publications

Zero-Inflated Patent Data Analysis Using Compound Poisson Models

Zero-Inflated Patent Data Analysis Using Compound Poisson Models

Patent Keyword Analysis Using Time Series and Copula Models

Proposing Robust LAD-Atan Penalty of Regression Model Estimation for High Dimensional Data

Contact Info

Product

Resources

About