Text classification: neural networks vs support vector machines

Journal of University of Shanghai for Science and Technology, 2021

One of the most trending and major areas of research in Natural Language Processing (NLP) is the classification of text data. This necessarily means that the category that the text belongs to is determined by the content of the text. Various algorithms such as Recurrent Neural Network along with its variation which is Long Short-Term Memory, Hierarchical Attention Networks and also Convolutional Neural Network have been used to analyse how the context of the text can be determined from the text data which in available in terms of datasets. These algorithms each have a special characteristic of their own. While Recurrent Neural Network maintains the structural sequence of the contexts, the Convolutional Neural Network manages to obtain the n-gram feature and the Hierarchical Attention Network manages the hierarchy of the documents or data. The above said algorithms have been implemented on the British Broadcasting Corporation News datasets. Various parameters such as recall, precisio...

36th Annual Hawaii International Conference on System Sciences, 2003. Proceedings of the

Text categorization is the process of sorting text documents into one or more predefined categories or classes of similar documents. Differences in the results of such categorization arise from the feature set chosen to base the association of a given document with a given category. Advocates of text categorization recognize that the sorting of text documents into categories of like documents reduces the overhead required for fast retrieval of such documents and provides smaller domains in which the users may explore similar documents. In this paper we are interested in examining whether automatic classification of news texts can be improved by a prefiltering the vocabulary to reduce the feature set used in the computations. First we compare artificial neural network and support vector machine algorithms for use as text classifiers of news items. Secondly, we identify a reduction in feature set that provides improved results.

Computational Linguistics

International Journal of Advance Research, Ideas and Innovations in Technology, 2021

Cyberspace has elevated business insights and created a virtual space to store all forms of information online. Due to the rapid development in the online world, the usage of digital documents has increased because it is comfortable for the users to share, update or keep track of the records in one place without losing data. However, maintaining massive data does not suit optimal decision-making and is extremely expensive for storage, processing, and collection. There is a gigantic possibility that human annotators make errors while classifying data because of distraction, monotony, fatigue, and failure to meet the requirements. Once the text classification method uses machine learning approaches, the process will execute with fewer mistakes and more accuracy. The main goal of this review paper is to highlight and explain the role of different machine learning methodologies in text classification. Concurrently, this paper describes the challenges faced by other machine learning techniques and text representation. Furthermore, this review paper will provide an extensive survey on how various machine learning techniques such as Neural Networks, Naive Bayes, Logistic Regression, Random Forest, Decision Trees, and Support Vector Machine (SVM)-are implemented in Text classification.

2002

International journal of engineering research and technology, 2019

In today’s world, the usage of digitalized text documents has drastically increased. The reason behind this is the growing need for portability of text related files and the greater need to eliminate the dependence on paper. Previously, the task of document classification was handled by very experienced experts who are capable of classifying large text documents into their corresponding category. Overtime, it was realized that this task extremely time consuming. Therefore the need for automatic text document classification came into the big picture. Corresponding research has shown the involvement of various classification algorithms to create an automated text document classification system. The major tasks involved in creating this type of automated system is handling large amount of texts, selecting the features from a wide range of availability and eventually selecting the classification algorithm which is best suited for classification text files. Initially the predefined class...

Journal of Advances in Information Technology, 2010

With the increasing availability of electronic documents and the rapid growth of the World Wide Web, the task of automatic categorization of documents became the key method for organizing the information and knowledge discovery. Proper classification of e-documents, online news, blogs, e-mails and digital libraries need text mining, machine learning and natural language processing techniques to get meaningful knowledge. The aim of this paper is to highlight the important techniques and methodologies that are employed in text documents classification, while at the same time making awareness of some of the interesting challenges that remain to be solved, focused mainly on text representation and machine learning techniques. This paper provides a review of the theory and methods of document classification and text mining, focusing on the existing literature.

Journal of Systems Science and Systems Engineering, 2007

Text mining, also known as discovering knowledge from the text, which has emerged as a possible solution for the current information explosion, refers to the process of extracting non-trivial and useful patterns from unstructured text. Among the general tasks of text mining such as text clustering, summarization, etc, text classification is a subtask of intelligent information processing, which employs unsupervised learning to construct a classifier from training text by which to predict the class of unlabeled text. Because of its simplicity and objectivity in performance evaluation, text classification was usually used as a standard tool to determine the advantage or weakness of a text processing method, such as text representation, text feature selection, etc. In this paper, text classification is carried out to classify the Web documents collected from XSSC Website (). The performance of support vector machine (SVM) and back propagation neural network (BPNN) is compared on this task. Specifically, binary text classification and multi-class text classification were conducted on the XSSC documents. Moreover, the classification results of both methods are combined to improve the accuracy of classification. An experiment is conducted to show that BPNN can compete with SVM in binary text classification; but for multi-class text classification, SVM performs much better. Furthermore, the classification is improved in both binary and multi-class with the combined method.

2019

Classification is a supervised learning method: the goal is finding the labels of the unknown object. In the real world, the tedious amounts of manual works are required to label the unknown documents. The system is initially trained by labeled documents by using one of the supervise machine learning algorithm and then applied trained model to predict the label of the unknown documents. The framework of text document classification consists of: input text document, pre-processing, feature extraction and classification. The analysis four common classification methods are performed: Naive Bayes, Decision Tree, Support Vector Machine and K-nearest neighbors for text document classification. The main focus of this paper is to present comparative study of different exiting classification methods for text document classification. The experiment performed different classification methods on the Enron Email Dataset and measure classification accuracy, true positive, true negative, false po...

2015

The paper presents an empirical study of three text classification algorithms using two datasets. Naïve Bayes, Support Vector Machine and C4.5 have been compared by training the dataset instances on the Weka Tool. The two datasets are Diabetes and Calories. Diabetes dataset has a large number of training examples and attributes as compared to the Calories dataset. The results are compared based on the recall and precision values that each of the algorithms are returning. Another basis of comparison is the percentage split of the dataset into training set and test set. Results show that out of the three classifiers, SVM is computationally efficient. SVM has certain disadvantages which degrades its performance for small datasets. Thus, it is proposed that using Hybrid SVM may improve the existing drawbacks of SVM. Even if the approach with which SVM is applied on the dataset is changed, it can produce optimized results.