Classification of confidential documents by using adaptive neurofuzzy inference systems

Alparslan, Erdem; Karahoca, Adem; Bahşi, Hayretdin

doi:10.1016/j.procs.2011.01.023

Cited by 9 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A study conducted by Alparslan et al [21] aimed to perform information extraction from documents classified within Turkish language. First, they extract word stems using stemming algorithms which are particularly used for Turkish text documents.…”

Section: Related Workmentioning

confidence: 99%

TTC-3600: A new benchmark dataset for Turkish text categorization

Kılınç

Özçift

Bozyiğit

et al. 2015

Journal of Information Science

View full text Add to dashboard Cite

Owing to the rapid growth of the World Wide Web, the number of documents that can be accessed via the Internet explosively increases with each passing day. Considering news portals in particular, sometimes documents related to categories such as technology, sports and politics seem to be in the wrong category or documents are located in a generic category called others. At this point, text categorization (TC), which is generally addressed as a supervised learning task is needed. Although there are substantial number of studies conducted on TC in other languages, the number of studies conducted in Turkish is very limited owing to the lack of accessibility and usability of datasets created. In this paper, a new dataset named TTC-3600, which can be widely used in studies of TC of Turkish news and articles, is created. TTC-3600 is a well-documented dataset and its file formats are compatible with well-known text mining tools. Five widely used classifiers within the field of TC and two feature selection methods are evaluated on TTC-3600. The experimental results indicate that the best accuracy criterion value 91.03% is obtained with the combination of Random Forest classifier and attribute ranking-based feature selection method in all comparisons performed after pre-processing and feature selection steps. The publicly available TTC-3600 dataset and the experimental results of this study can be utilized in comparative experiments by other researchers.

show abstract

Section: Related Workmentioning

confidence: 99%

TTC-3600: A new benchmark dataset for Turkish text categorization

Kılınç

Özçift

Bozyiğit

et al. 2015

Journal of Information Science

View full text Add to dashboard Cite

show abstract

“…One such feature weighting technique is tf-idf ; tf-idf assigns the weight to the term based on its frequency in a document, and its appearance in all documents in the corpus. The assigned weight indicates the relevancy of that term to the document when classifying the documents into different classes [ 21 , 24 , 25 ]. The higher value of the term indicates its higher importance.…”

Section: Methodsmentioning

confidence: 99%

Automatic Incident Triage in Radiation Oncology Incident Learning System

et al. 2020

View full text Add to dashboard Cite

The Radiotherapy Incident Reporting and Analysis System (RIRAS) receives incident reports from Radiation Oncology facilities across the US Veterans Health Affairs (VHA) enterprise and Virginia Commonwealth University (VCU). In this work, we propose a computational pipeline for analysis of radiation oncology incident reports. Our pipeline uses machine learning (ML) and natural language processing (NLP) based methods to predict the severity of the incidents reported in the RIRAS platform using the textual description of the reported incidents. These incidents in RIRAS are reviewed by a radiation oncology subject matter expert (SME), who initially triages some incidents based on the salient elements in the incident report. To automate the triage process, we used the data from the VHA treatment centers and the VCU radiation oncology department. We used NLP combined with traditional ML algorithms, including support vector machine (SVM) with linear kernel, and compared it against the transfer learning approach with the universal language model fine-tuning (ULMFiT) algorithm. In RIRAS, severities are divided into four categories; A, B, C, and D, with A being the most severe to D being the least. In this work, we built models to predict High (A & B) vs. Low (C & D) severity instead of all the four categories. Models were evaluated with macro-averaged precision, recall, and F1-Score. The Traditional ML machine learning (SVM-linear) approach did well on the VHA dataset with 0.78 F1-Score but performed poorly on the VCU dataset with 0.5 F1-Score. The transfer learning approach did well on both datasets with 0.81 F1-Score on VHA dataset and 0.68 F1-Score on the VCU dataset. Overall, our methods show promise in automating the triage and severity determination process from radiotherapy incident reports.

show abstract

“…A study conducted by Alparslan et al (2011) aimed to extract information from documents that were classified within the Turkish language. First, word stems were extracted using stemming algorithms which were particularly employed for Turkish text documents.…”

Section: Text Classification In Turkish Languagementioning

confidence: 99%

MooDetecTR: Kelime Vektörleri Vasıtasıyla Türkçe Şarkı Sözleri için Ruh Hali Tespiti

Cimen

Durahim

2020

Konya Journal of Engineering Sciences

View full text Add to dashboard Cite

Along with the increasing use of online music platforms, catalogue-based searches have turned into mood-based seeking. In this study, we propose MooDetecTR, a semi-supervised learning framework that employs word vectors for Turkish song mood detection. In this framework, first word vectors are created through a large collection of textual data, which include more than 2.5 million Turkish documents, by using Word2Vec and GloVe algorithms. Subsequently, lyrics vectors are generated through combining already trained word vectors of the words in the lyrics selected for mood detection. Lastly, lyrics vectors are fed into various machine-learning algorithms as features to create models for music mood detection. For comparison, Turkish music mood detection is performed both via traditional bag-of-words model, with TF-IDF weights, and Doc2Vec algorithm. The effects of stemming of the words and stop-words removal on the results are investigated, as well. The best micro-f1 score (54.36%) obtained by the proposed framework is 3.81%, and 2.92% higher (7.54%, and 5.68% relative improvements) than the best score obtained from Doc2Vec and bag-of-words methods, respectively. Consequently, the results obtained show the effectiveness of incorporating word vectors generated using big textual data into Turkish text classification process, which is clearly illustrated by the improved classification performance.

show abstract

Classification of confidential documents by using adaptive neurofuzzy inference systems

Cited by 9 publications

References 4 publications

TTC-3600: A new benchmark dataset for Turkish text categorization

TTC-3600: A new benchmark dataset for Turkish text categorization

Automatic Incident Triage in Radiation Oncology Incident Learning System

MooDetecTR: Kelime Vektörleri Vasıtasıyla Türkçe Şarkı Sözleri için Ruh Hali Tespiti

Contact Info

Product

Resources

About