The Role of Rare Terms in Enhancing the Performance of Polynomial Networks Based Text Categorization

Abstract

<span>In this paper, the role of rare or infrequent terms in enhancing the accuracy of English Text Categorization using Polynomial Networks (PNs) is investigated. To study the impact of rare terms in enhancing the accuracy of PNs-based text categorization, different term reduction criteria as well as different term weighting schemes were experimented on the Reuters Corpus using PNs. Each term weighting scheme on each reduced term set was tested once keeping the rare terms and another time removing them. All the experiments conducted in this research show that keeping rare terms substantially improves the performance of Polynomial Networks in Text Categorization, regardless of the term reduction method, the number of terms used in classification, or the term weighting scheme adopted.</span> <p> <span></span> </p

The Significance Of Low Frequent Terms in Text Classification

“…The significance of low frequent terms in TC performance was always debatable. A recent study has proved that keeping low frequent terms can enhance polynomial networks (PN)‐based TC of the Reuters Data Set to a great extent, regardless of the term‐weighting scheme adopted or the term‐reduction method used . The enhancement on the accuracy recorded when keeping the low frequent terms in this research was great; it reached 17% in some experiments.…”

“…The research conducted in Ref. is extended here to investigate the significance of low frequent terms in TC using other state‐of‐the‐art TC algorithms. Furthermore, additional performance measures are used here to investigate the significance of low frequent terms in TC.…”

Arabic Text Categorization Using Logistic Regression

“…Chi Square (CHI) is used in the experiments of this research as a FS metric for selecting the most discriminating features in the dataset. CHI has proved to record high accuracy in classifying both English [7,6,16,[61][62][63][64][65][66] and Arabic [5,6,16,[55][56][57][58] texts. The CHI FS metric measures the lack of independence between a term and a class.…”

“…After deciding on the terms to be selected for building the classifier, the terms will be represented in the categorization system using one of the various presentations or weights used in the literature of TC. [3,5,9,14,56,59], Term Frequency (TF) [14,15,55,57,58], Document Frequency (DF) [55], Weighted IDF [14], Normalized Frequency [7,16,[60][61][62][63][64], Boolean [6,55,61,62,64] and other FS methods like Cosine coefficient, Dice coefficient and Jacaard coefficient [68]. In this research, Normalized frequency is used to as a weighting scheme for term representation in the Vector Space Model.…”

“…A class-based local policy is applied, in this research, for selecting the best terms for building all the classifiers by selecting 1% of the topmost terms from each of the five classes. This policy has proved to achieve the best categorization performance compared to other reduction policies, like choosing the topmost corpus terms, or an equal number of terms from each class, as it gives each class a representative share in the final set of terms used to build the classifier [16,[61][62][63][64]69]. The number of terms selected from each class and the total number of terms, after applying CHI and Feature Reduction, then removing duplicates is summarized in Table 3.…”