A symmetric term weighting scheme for text categorization based on term occurrence probabilities

Erenel, Zafer; Altınçay, Hakan; Varoğlu, Ekrem

doi:10.1109/icsccw.2009.5379438

Cited by 5 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From this perspective, the gain by the use of a function of together with RF can be considered as small. However, it should be noted that, when the term frequency (tf ) is used alone without any other weight, the Macro-F 1 score is obtained as 88.39 on Reuters-21578 dataset [23]. In other words, the gain provided by the state-of-the-art scheme, tf × RF is 1.07.…”

Section: Discussionmentioning

confidence: 98%

“…In the case of RF χ 2 , it can be seen that a better F 1 score is achieved only on WebKB whereas the score on Reuters-21578 is inferior compared to χ 2 . It should be remembered that RF is an asymmetric scheme where, for a given value, the weights decrease as β increases [23]. On the other hand, χ 2 is a symmetric scheme where the weights decrease as β increases from zero to one and increases for increasing values of β when β > 1.…”

Section: Experimental Workmentioning

confidence: 98%

See 1 more Smart Citation

Using the absolute difference of term occurrence probabilities in binary text categorization

Altınçay

Erenel

2010

Appl Intell

Self Cite

View full text Add to dashboard Cite

In this study, the differences among widely used weighting schemes are studied by means of ordering terms according to their discriminative abilities using a recently developed framework which expresses term weights in terms of the ratio and absolute difference of term occurrence probabilities. Having observed that the ordering of terms is dependent on the weighting scheme under concern, it is emphasized that this can be explained by the way different schemes use term occurrence differences in generating term weights. Then, it is proposed that the relevance frequency which is shown to provide the best scores on several datasets can be improved by taking into account the way absolute difference values are used in other widely used schemes. Experimental results on two different datasets have shown that improved F 1 scores can be achieved.

show abstract

Section: Discussionmentioning

confidence: 98%

Section: Experimental Workmentioning

confidence: 98%

Using the absolute difference of term occurrence probabilities in binary text categorization

Altınçay

Erenel

2010

Appl Intell

Self Cite

View full text Add to dashboard Cite

show abstract

“…The authors proposed three new TWS for QC and analysed their behaviour for TC. In [57], authors proposed that TWS can also be considered as term occurrence probabilities in +ve and 2ve categories.…”

Section: Related Workmentioning

confidence: 99%

Enhancing comprehensibility of software clustering results

Siddique

Maqbool

2012

IET Softw.

View full text Add to dashboard Cite

As requirements of organisations change, so do the software systems within them. When changes are carried out under tough deadlines, software developers often do not follow software engineering principles, which results in deteriorated structure of the software. A badly structured system is difficult to understand for further changes. To improve structure, re-modularisation may be carried out. Clustering techniques have been used to facilitate automatic re-modularisation. However, clusters produced by clustering algorithms are difficult to comprehend unless they are labelled appropriately. Manual assignment of labels is tiresome, thus efforts should be made towards automatic cluster label assignment. In this study, the authors focus on facilitating comprehension of software clustering results by automatically assigning meaningful labels to clusters. To assign labels, the authors use term weighting schemes borrowed from the domain of information retrieval and text categorisation. Although some term weighting schemes have been used by researchers for software cluster labelling, there is a need to analyse the term weighting schemes and related issues to identify the strengths and weaknesses of these schemes for software cluster labelling. In this context, the authors analyse the behaviour of seven well-known term weighting schemes. Also, they perform the experiments on five software systems to identify software characteristics which affect the labelling behaviour of the term weighting schemes.

show abstract

“…Ignoring the priori class probability ratio, the classification task can be achieved by the matching score function, 19 (5) where N u is the term frequency of w u in the document, 1u is the Multinomial parameter of the positive class, and 0u is the Multinomial parameter of the negative one. After replacing the parameters by their Bayesian estimators, we have a new scheme as…”

Section: Relevance Term Frequency Weighing Schemementioning

confidence: 99%

“…It helps to adjust for the fact that some words appear more frequently in general and is known as the global weight (or, the collection frequency factor). [4][5][6] However, tf-idf is not the best choice for a supervised learning task, in which the labels of the training documents contain important information. 4 Using these information, supervised term weighting methods can assign larger weights to the discriminative terms among different classes, and have gained increasing attention since the beginning of the new century.…”

Section: Introductionmentioning

confidence: 99%

A Term Frequency Based Weighting Scheme Using Naïve Bayes for Text Classification

Feng¹,

Wang²,

Sun³

et al. 2016

j comput theor nanosci

View full text Add to dashboard Cite

Term weighting is a strategy to assign weights to terms to improve the performance of many classifiers, such as kNN and SVM in text classification. Supervised term weighting methods have received increasing attention, in which information on the membership of training documents to classes is used. Most existing methods follow the local weight multiplies the global weight framework, but the contribution of term frequency for term weighting has not been fully investigated. In this paper, we propose a weighting scheme named term frequency-relevance term frequency based on a probabilistic model. After investigating two kinds of widely used naïve Bayes (NB) models, we employ the term event Multinomial NB model to capture the term frequency information. The matching score function based on the prediction probability ratio can then be factorized. Finally, we get the weight for each term by replacing the parameter by an estimator, term frequency is used in formulating not only the local weight factor but also the global weight factor. Numerical experiment results on two benchmark text datasets (Reuters-21578 and 20 Newsgroups) demonstrate that our proposed method outperforms the representative term weighting methods.

show abstract

A symmetric term weighting scheme for text categorization based on term occurrence probabilities

Cited by 5 publications

References 8 publications

Using the absolute difference of term occurrence probabilities in binary text categorization

Using the absolute difference of term occurrence probabilities in binary text categorization

Enhancing comprehensibility of software clustering results

A Term Frequency Based Weighting Scheme Using Naïve Bayes for Text Classification

Contact Info

Product

Resources

About