Comparison of Support Vector Machines With and Without Latent Semantic Analysis for Document Classification

Khatavkar, Vaibhav; Kulkarni, Parag

doi:10.1007/978-981-13-1402-5_20

Cited by 3 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Berdasarkan pengujian, komposisi data latih dan data uji yang terbaik adalah 80:20 dengan akurasi sebesar 64%. Namun, dibandingkan dengan [6], akurasi klasifikasi menggunakan kombinasi SVM-LSA memiliki nilai akurasi lebih rendah (lihat Tabel 2). Hal ini karena LSA melakukan ekstraksi fitur sehingga dimungkinkan menghapus kata kunci penting yang mengindikasikan konten web anak.…”

Section: Resultsunclassified

“…Oleh karena itu, perlu dilakukan eksperimen pada perbaikan metode LSA atau dapat menggunakan metode ekstraksi fitur yang lain. Namun, LSA memungkinkan berkurangnya dimensi dataset sehingga meningkatkan efisiensi proses klasifikasi [6].…”

Section: Resultsunclassified

“…Penelitian [6] juga memilih metode SVM untuk klasifikasi dokumen dengan jumlah dataset besar. Data yang digunakan dalam klasifikasi adalah data berita dari web BBC yang telah dikategorikan ke dalam 5 (lima) kelas yaitu bisnis, entertainment, teknologi, olahraga, dan politik sebanyak 2225 dokumen.…”

Section: Introductionunclassified

“…LSA digunakan untuk mengekstrak hubungan semantik umum antara kata kunci dengan dokumen. Pada [6] juga dilakukan percobaan mengkombinasikan SVM dengan LSA menggunakan 2 (dua) jenis dataset. Dari kedua dataset yang diuji, kombinasi SVM dan LSA mampu melakukan klasifikasi dengan efisiensi waktu yang lebih baik dibandingkan jika hanya menggunakan SVM.…”

Section: Introductionunclassified

See 3 more Smart Citations

Content Classification based-on Latent Semantic Analysis and Support Vector Machine (LSA-SVM)

Marthasari

Hayatin

Yuniarti

2022

View full text Add to dashboard Cite

The diversity of the content of a web page can have a negative impact if used by the wrong user. Almost a half of internet users are children. Therefore, it is important to classify web pages to find out which pages are worthy of being seen by children and that are not feasible. One method that can be used is the Support Vector Machine (SVM) algorithm. SVM is a binary classification whose working principle is to find the best hyperplane to separate the two classes. To obtain better classification accuracy, the SVM is combined with the Latent Semantic Analysis (LSA) algorithm. The data used in this study were taken from the DMOZ web data which has been classified into two categories. The data is then entered into the pre-processing stage for further feature extraction using LSA. The LSA algorithm is used to find out the semantic similarities of words and text contained in web pages. The results of feature extraction are then classified using SVM with RBF kernel. Based on the testing result, we obtain a classification accuracy of 64%.

show abstract

Section: Resultsunclassified

Section: Introductionunclassified

See 2 more Smart Citations

Content Classification based-on Latent Semantic Analysis and Support Vector Machine (LSA-SVM)

Marthasari

Hayatin

Yuniarti

2022

View full text Add to dashboard Cite

show abstract

“…However, this is not sufficient to select a particular algorithm. In [8], Khatavkar and Kulkarni explain efficiency of SVM on news dataset with respect to time. This motivates the researchers to have a multi-perspective analysis of text data using machine learning algorithms.…”

Section: Nearest Neighborsmentioning

confidence: 99%

Multi-Perspective Analysis of News Articles using Machine Learning Algorithms

Khatavkar¹,

Velankar²,

Kulkarni³

2019

IJCA

Self Cite

View full text Add to dashboard Cite

Nowadays, many machine learning algorithms are evolving. It is a very difficult task to select a particular algorithm for a specific problem. A multi-perspective analysis of the given input data has to be performed to select a particular algorithm. In this study a case study has been taken for selecting an algorithm for the classification of news articles. Multiperspective analysis is performed on the data using various machine learning algorithms namely Random Forest Classifier, Decision tree, AdaBoostClassifier, SVM with Linear SVC and SVM with NuSVC. For the multi perspective analysis, features from the dataset are extracted and standard metrics are used. The metrics used are Kappa, Accuracy, Fmeasure, Recall, and Precision. For the BBC news standard dataset, SVM Linear SVC proves to be effective because its classification rate is 96% and false positive rate is 0.75%.

show abstract