• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.2
• /
• pp.604-625
• /
• 2018

Nowadays, SMS spam has been overflowing in many countries. In fact, the standards of filtering SMS spam are different from country to country. However, the current technologies and researches about SMS spam filtering all focus on dividing SMS message into two classes: legitimate and illegitimate. It does not conform to the actual situation and need. Furthermore, they are facing several difficulties, such as: (1) High quality and large-scale SMS spam corpus is very scarce, fine categorized SMS spam corpus is even none at all. This seriously handicaps the researchers' studies. (2) The limited length of SMS messages lead to lack of enough features. These factors seriously degrade the performance of the traditional classifiers (such as SVM, K-NN, and Bayes). In this paper, we present a new fine categorized SMS spam corpus which is unique and the largest one as far as we know. In addition, we propose a classifier, which is based on the probability topic model. The classifier can alleviate feature sparse problem in the task of SMS spam filtering. Moreover, we compare the approach with three typical classifiers on the new SMS spam corpus. The experimental results show that the proposed approach is more effective for the task of SMS spam filtering.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.7
• /
• pp.271-276
• /
• 2014

Short message service(SMS) in a mobile communication environment is a very convenient method. However, it caused a serious side effect of generating spam messages for advertisement. Those who send spam messages distort or deform SMS sentences to avoid the messages being filtered by automatic filtering system. In order to increase the performance of spam filtering system, we need to recover the distorted sentences into normal sentences. This paper proposes a method of normalizing the various types of distorted sentence and extracting keywords through automatic word spacing and compound noun decomposition.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.9B
• /
• pp.908-913
• /
• 2009

Mobile phones became important household appliance that cannot be without in our daily lives. And the short messaging service (SMS) in these mobile phones is 1.5 to 2 times more than the voice service. However, the spam filtering functions installed in mobile phones take a method to receive specific number patterns or words and recognize spam messages when those numbers or words are present. However, this method cannot properly filters various types of spam messages currently dispatched. This paper proposes a more powerful and more adaptive spam filtering system using SVM and thesaurus. The system went through a process of isolating words from sample data through pro-processing device and integrating meanings of isolated words using a thesaurus. Then it generated characteristics of integrated words through the chi-square statistics and studied the characteristics. The proposed system is realized in a Window environment and the performance is confirmed through experiments.

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.95-99
• /
• 2014

본 논문에서는 최근 급속히 증가하여 사회적 이슈가 되고 있는 SMS 스팸 필터링을 위한 듀얼 SMS 스팸필터링 기법을 제안한다. 지속적으로 증가하고 새롭게 변형되는 SMS 문자 필터링을 위해서는 패턴 및 스팸 단어 사전을 통한 필터링은 많은 수작업을 요구하여 부적합하다. 그리하여 기계 학습을 이용한 자동화 시스템 구축이 요구되고 있으며, 효과적인 기계 학습을 위해서는 자질 선택과 자질의 가중치 책정 방법이 중요하다. 하지만 SMS 문자 특성상 문장들이 짧기 때문에 출현하는 자질의 수가 적어 분류의 어려움을 겪게 된다. 이 같은 문제를 개선하기 위하여 본 논문에서는 슬라이딩 윈도우 기반 N-gram 확장을 통해 자질을 확장하고, 확장된 자질로 그래프를 구축하여 얕은 구조적 특징을 표현한다. 학습 데이터에 출현한 N-gram 자질을 정점(Vertex)으로, 자질의 출현 빈도를 그래프의 간선(Edge)의 가중치로 설정하여 햄(HAM)과 스팸(SPAM) 그래프를 각각 구성한다. 이렇게 구성된 그래프를 바탕으로 노드의 중요도와 간선의 가중치를 활용하여 최종적인 자질의 가중치를 결정한다. 입력 문자가 도착하면 스팸과 햄의 그래프를 각각 이용하여 입력 문자의 2개의 자질 벡터(Vector)를 생성한다. 생성된 자질 벡터를 지지 벡터 기계(Support Vector Machine)를 이용하여 각 SVM 확률 값(Probability Score)을 얻어 스팸 여부를 결정한다. 3가지의 실험환경에서 바이그램 자질과 이진 가중치를 사용한 기본 시스템보다 F1-Score의 약 최대 2.7%, 최소 0.5%까지 향상되었으며, 결과적으로 평균 약 1.35%의 성능 향상을 얻을 수 있었다.

• Annual Conference on Human and Language Technology
• /
• 2008.10a
• /
• pp.195-200
• /
• 2008

본 논문에서는 형태소 분석을 이용한 확률 기반 한국어 SMS 스팸 필터링 기법을 제안한다. 기존 연구에서는 단어 및 문자 단위 어휘 정보를 자질로 이용한 영어 및 스페인어 SMS 스팸 필터링 방법들이 있다. 하지만 교착어인 한국어의 경우, 어근과 접사의 조합에 의해서 다양한 어절이 형성될 수 있다. 따라서 어절단위 어휘 정보를 자질로 사용할 경우, 미등록어(out of vocabulary) 문제가 발생한다. 특히, 매우 적은 수의 단어들로 구성된 SMS 메시지의 경우에는 이 문제가 매우 심각하다. 본 논문에서는 형태소 분석을 이용하여 이러한 문제점을 해결하고자 하였다. 실험 결과, 제안하는 방법은 기존 연구와 비교하여 10.6%의 스팸 분류 정확률 향상을 보였다. 또한 미등록어만을 포함하는 SMS 메시지의 수는 약 77% 감소하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.219-222
• /
• 2011

본 논문에서는 스팸 SMS 발신번호와 메시지 텍스트의 특징을 기계학습한 스팸 필터링 시스템을 논한다. 최근 변화하는 스팸SMS에 대한 적응력을 위해서, 각 트레이닝 셋의 수신 텍스트를 음절단위로 분석 할 것을 제안한다. 그리고 기존의 분류기는 성능이 미흡하거나 구현의 복잡성으로 인해 실제로 스펨 필터엔진으로 활용되지 않는 점을 극복하기 위해서 보다 단순한 분류기를 사용한다. 제안하는 시스템은 트레이닝 셋의 발신번호 및 수신 텍스트의 음절단위를 빈도수와 묶어 학습데이터를 구성하고, 테스트 셋을 스팸적 논스팸적으로 분석하여 스팸일 확률을 계산한다. 또한 Naive baysian를 바탕으로 한 경계값 기반 분류기를 통해, 타 분류기에 비해 구현 및 활용면에서 실용성이 높으면서도 성능이 뒤처지지 않는 시스템을 제안한다.

• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1397-1409
• /
• 2017

For text categorization task, distinctive text features selection is important due to feature space high dimensionality. It is important to decrease the feature space dimension to decrease processing time and increase accuracy. In the current study, for text categorization task, we introduce a novel statistical feature selection approach. This approach measures the term distribution in all collection documents, the term distribution in a certain category and the term distribution in a certain class relative to other classes. The proposed method results show its superiority over the traditional feature selection methods.

• Journal of Digital Contents Society
• /
• v.16 no.5
• /
• pp.815-822
• /
• 2015

By the growing of SMS phishing victims, applications for processing spam messages are being released in succession. However most spam messages that cleverly modified the content like separating the consonants and vowels are fail to be filtered. In this paper, we implemented an application 'AntiSpam' which is able to identify spam strings in the text message to solve this problem. 'AntiSpam' searches spam strings in the text message by using set-based POI search algorithm, and then calculate the possibility of whether it is spam or not in accordance with the search results. In addition, it catches skillfully disguised spam messages in order to avoid missing the spam filtering. Users, who received a message, can check the result in spam message possibility decision result and the contents of the message and they can choose how to handling the message.

• Proceedings of the KIEE Conference
• /
• 2003.07a
• /
• pp.259-261
• /
• 2003

This paper suggests wireless diagnosis and monitoring system using SMS mode of mobile communication network for distribution transformer which could prevent electrical accident in the near future. Data are acquired by measuring the temperature of insulator oil in the distribution transformer and load current. Data acquisition of sensor using mobile communication network carried out filtering of sensor's output to optimize the size of send data Merit of this inspection method is that management, control and monitoring some transformers can be carried out using only one server. This inspection method will be the way of inspection to be worth spotlight in the near future because it is able to solve easily with the minimum facility inspection about state of transformer which is operating, to wide coverage about machine's wrong operation in other field.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.24-29
• /
• 2018

Text analysis technique for natural language processing in deep learning represents words in vector form through word embedding. In this paper, we propose a method of constructing a document vector and classifying it into spam and normal text message, using word embedding and deep learning method. Automatic spacing applied in the preprocessing process ensures that words with similar context are adjacently represented in vector space. Additionally, the intentional word formation errors with non-alphabetic or extraordinary characters are designed to avoid being blocked by spam message filter. Two embedding algorithms, CBOW and skip grams, are used to produce the sentence vector and the performance and the accuracy of deep learning based spam filter model are measured by comparing to those of SVM Light.