Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381889306> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4381889306 abstract "Abstract The work presents robust statistical and exploratory analysis to demonstrate the effects of performances of machine learning (ML) classifiers and sampling techniques in document datasets. 1,000 portable document format (PDF) files are divided into five labels from the World Health Organization COVID-19 Research Downloadable Articles and PubMed Central databases for positive and negative papers. PDF files are converted into unstructured raw text files and pre-processed before tokenization. Training size and subsampling were varied experimentally to determine their effect on the performance measures, such as accuracy, precision, recall, and AUC. Supervised classification is performed using the Random Forest, Naïve Bayes, Decision Tree, XGBoost, and Logistic Regression. Imbalanced sampling techniques are implemented using the Synthetic Minority Oversampling Technique, Random Oversampling, Random Undersampling, TomekLinks, and NearMiss to address the problem of distribution of positive and negative samples. R and the tidyverse are used to conduct statistical and exploratory data analysis on performance metrics. The ML classifiers achieve an average precision score of 78% and a recall score of 77%, while the sampling techniques have higher average precision and recall scores of 80% and 81%, respectively. Correcting imbalanced sampling supplied significant p-values from NearMiss, ROS, and SMOTE for precision and recall scores. This work has shown with statistical significance including the analysis of variance (ANOVA) that training size variation, subsampling, and imbalanced sampling techniques with ML algorithms can improve performances in document datasets." @default.
- W4381889306 created "2023-06-25" @default.
- W4381889306 creator A5065064280 @default.
- W4381889306 creator A5047961473 @default.
- W4381889306 date "2023-06-24" @default.
- W4381889306 modified "2023-09-27" @default.
- W4381889306 title "Machine Learning for Detecting Trends and Topics from Research Papers and Proceedings in Biomedical Literature" @default.
- W4381889306 cites W1966413371 @default.
- W4381889306 cites W1990106316 @default.
- W4381889306 cites W2002505925 @default.
- W4381889306 cites W2080445080 @default.
- W4381889306 cites W2084789715 @default.
- W4381889306 cites W2106365165 @default.
- W4381889306 cites W2119191234 @default.
- W4381889306 cites W2148143831 @default.
- W4381889306 cites W2512104237 @default.
- W4381889306 cites W2894747149 @default.
- W4381889306 cites W2995715529 @default.
- W4381889306 cites W3021175879 @default.
- W4381889306 cites W3081088023 @default.
- W4381889306 cites W3098603383 @default.
- W4381889306 cites W4210247351 @default.
- W4381889306 cites W4223614374 @default.
- W4381889306 cites W4288442043 @default.
- W4381889306 cites W54464883 @default.
- W4381889306 doi "https://doi.org/10.21203/rs.3.rs-3054886/v1" @default.
- W4381889306 hasPublicationYear "2023" @default.
- W4381889306 type Work @default.
- W4381889306 citedByCount "0" @default.
- W4381889306 crossrefType "posted-content" @default.
- W4381889306 hasAuthorship W4381889306A5047961473 @default.
- W4381889306 hasAuthorship W4381889306A5065064280 @default.
- W4381889306 hasBestOaLocation W43818893061 @default.
- W4381889306 hasConcept C100660578 @default.
- W4381889306 hasConcept C105795698 @default.
- W4381889306 hasConcept C106131492 @default.
- W4381889306 hasConcept C119857082 @default.
- W4381889306 hasConcept C12267149 @default.
- W4381889306 hasConcept C124101348 @default.
- W4381889306 hasConcept C136536468 @default.
- W4381889306 hasConcept C140779682 @default.
- W4381889306 hasConcept C154945302 @default.
- W4381889306 hasConcept C15744967 @default.
- W4381889306 hasConcept C169258074 @default.
- W4381889306 hasConcept C180747234 @default.
- W4381889306 hasConcept C197323446 @default.
- W4381889306 hasConcept C2776257435 @default.
- W4381889306 hasConcept C31258907 @default.
- W4381889306 hasConcept C31972630 @default.
- W4381889306 hasConcept C33923547 @default.
- W4381889306 hasConcept C41008148 @default.
- W4381889306 hasConcept C52001869 @default.
- W4381889306 hasConcept C84525736 @default.
- W4381889306 hasConceptScore W4381889306C100660578 @default.
- W4381889306 hasConceptScore W4381889306C105795698 @default.
- W4381889306 hasConceptScore W4381889306C106131492 @default.
- W4381889306 hasConceptScore W4381889306C119857082 @default.
- W4381889306 hasConceptScore W4381889306C12267149 @default.
- W4381889306 hasConceptScore W4381889306C124101348 @default.
- W4381889306 hasConceptScore W4381889306C136536468 @default.
- W4381889306 hasConceptScore W4381889306C140779682 @default.
- W4381889306 hasConceptScore W4381889306C154945302 @default.
- W4381889306 hasConceptScore W4381889306C15744967 @default.
- W4381889306 hasConceptScore W4381889306C169258074 @default.
- W4381889306 hasConceptScore W4381889306C180747234 @default.
- W4381889306 hasConceptScore W4381889306C197323446 @default.
- W4381889306 hasConceptScore W4381889306C2776257435 @default.
- W4381889306 hasConceptScore W4381889306C31258907 @default.
- W4381889306 hasConceptScore W4381889306C31972630 @default.
- W4381889306 hasConceptScore W4381889306C33923547 @default.
- W4381889306 hasConceptScore W4381889306C41008148 @default.
- W4381889306 hasConceptScore W4381889306C52001869 @default.
- W4381889306 hasConceptScore W4381889306C84525736 @default.
- W4381889306 hasLocation W43818893061 @default.
- W4381889306 hasOpenAccess W4381889306 @default.
- W4381889306 hasPrimaryLocation W43818893061 @default.
- W4381889306 hasRelatedWork W3081746618 @default.
- W4381889306 hasRelatedWork W3127425528 @default.
- W4381889306 hasRelatedWork W3143658565 @default.
- W4381889306 hasRelatedWork W3176807344 @default.
- W4381889306 hasRelatedWork W3193372619 @default.
- W4381889306 hasRelatedWork W3204641204 @default.
- W4381889306 hasRelatedWork W4292651891 @default.
- W4381889306 hasRelatedWork W4319718059 @default.
- W4381889306 hasRelatedWork W4377964522 @default.
- W4381889306 hasRelatedWork W4381569929 @default.
- W4381889306 isParatext "false" @default.
- W4381889306 isRetracted "false" @default.
- W4381889306 workType "article" @default.