A Hybrid Document Features Extraction with Clustering based Classification Framework on Large Document Sets

Abstract

As the size of the document collections are increasing day-by-day, finding an essential document clusters for classification problem is one of the major problem due to high inter and intra document variations. Also, most of the conventional classification models such as SVM, neural network and Bayesian models have high true negative rate and error rate for document classification process. In order to improve the computational efficacy of the traditional document classification models, a hybrid feature extraction-based document cluster approach and classification approaches are developed on the large document sets. In the proposed work, a hybrid glove feature selection model is proposed to improve the contextual similarity of the keywords in the large document corpus. In this work, a hybrid document clustering similarity index is optimized to find the essential key document clusters based on the contextual keywords. Finally, a hybrid document classification model is used to classify the clustered documents on large corpus. Experimental results are conducted on different datasets, it is noted that the proposed document clustering-based classification model has high true positive rate, accuracy and low error rate than the conventional models.

Harnessing K-means Clustering to Decode Communication Patterns in Modern Electronic Devices

“…With [13][14][15] emphasizing the role of mobile network operators in managing IoT communication data and spotlighting the challenges in new media system analysis, the overarching theme becomes evident. There's an urgent need for a robust model that navigates the intricacies of device communication data and provides tangible insights for device functionality enhancement and security fortification [16][17][18][19][20]. This backdrop amplifies the motivation behind the proposed work, which aims to leverage the K-means clustering algorithm to decode intricate communication patterns from modern electronic devices [21][22][23].…”

Optimizing Document Classification: Unleashing the Power of Genetic Algorithms

“…The results of their experiments revealed that the CPAMF results were better than those of the cosine measure and BM25 by a healthy margin. For research article categorization, some authors have proposed hybrid approaches [19], [27], [28], [29], [30]. In these approaches, feature extraction is performed utilizing DL techniques and classification based on ML and DL methods.…”

“…These techniques can recognize the context of words in a research article, such as semantic and grammatical similarities, as well as correlations with other words. Owing to the increasing use of these techniques by researchers in different domains, the document classification community started the utilization of these techniques in their studies [14], [18], [19], [20] which presented promising results. One of the issues related to these techniques is the large length of the vector generated against a single word in a text.…”

A Comprehensive Evaluation of Metadata-Based Features to Classify Research Paper’s Topics

“…Comparison against the performance with SVM, Rocchio algorithm, Bayes, Naïve Bayes is mentioned in the paper, however, authors have not provided the table or graph results. Some authors proposed hybrid approaches for textual document classification [21] [22] [23]. In hybrid approaches, the algorithms focused on both feature extraction using deep learning and classification using machine and deep learning.…”