Pub Date : 2018-09-01DOI: 10.1109/ICDIM.2018.8847056
Deden Irfan Afryansyah, Magfirawaty, K. Ramli
Security is one of the most important aspects of the Internet of Things (IoT) due to the increasing trend of attacks in an IoT environment. Cryptographic techniques can be used to improve the security aspects of IoT implementation. Due to the limitations of computing resources in most devices connected to the IoT, reliable and efficient hash functions are required. In this paper, TWISH, a new hash design that can be efficiently implemented without compromising the security, is proposed. TWISH is based on the lightweight block cipher TWINE using the Davies-Meyer (DM) scheme. We analyze the security and randomness of the resulting output using the Cryptographic Randomness Test package. These tests include the Strict Avalanche Criterion (SAC), Collision, Coverage, and Linear Span test. The results show that TWISH can pass the applied tests. The tests also indirectly demonstrate that TWISH is quite resistant to near-collision, preimage, and differential/linear attacks.
{"title":"The Development and Analysis of TWISH: A Lightweight-Block-Cipher-TWINE-Based Hash Function","authors":"Deden Irfan Afryansyah, Magfirawaty, K. Ramli","doi":"10.1109/ICDIM.2018.8847056","DOIUrl":"https://doi.org/10.1109/ICDIM.2018.8847056","url":null,"abstract":"Security is one of the most important aspects of the Internet of Things (IoT) due to the increasing trend of attacks in an IoT environment. Cryptographic techniques can be used to improve the security aspects of IoT implementation. Due to the limitations of computing resources in most devices connected to the IoT, reliable and efficient hash functions are required. In this paper, TWISH, a new hash design that can be efficiently implemented without compromising the security, is proposed. TWISH is based on the lightweight block cipher TWINE using the Davies-Meyer (DM) scheme. We analyze the security and randomness of the resulting output using the Cryptographic Randomness Test package. These tests include the Strict Avalanche Criterion (SAC), Collision, Coverage, and Linear Span test. The results show that TWISH can pass the applied tests. The tests also indirectly demonstrate that TWISH is quite resistant to near-collision, preimage, and differential/linear attacks.","PeriodicalId":120884,"journal":{"name":"2018 Thirteenth International Conference on Digital Information Management (ICDIM)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124802017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ICDIM.2018.8847002
Lasitha Uyangoda, S. Ahangama, Tharindu Ranasinghe
A huge amount of user generated content related to movies is created with the popularization of web 2.0. With these continues exponential growth of data, there is an inevitable need for recommender systems as people find it difficult to make informed and timely decisions. Movie recommendation systems assist users to find the next interest or the best recommendation. In this proposed approach the authors apply the relationship of user feature-scores derived from user-item interaction via ratings to optimize the prediction algorithm’s input parameters used in the recommender system to improve the accuracy of predictions with less past user records. This addresses a major drawback in collaborative filtering, the cold start problem by showing an improvement of 8.4% compared to the base collaborative filtering algorithm. The user-feature generation and evaluation of the system is carried out using the ‘MovieLens 100k dataset’. The proposed system can be generalized to other domains as well.
{"title":"User Profile Feature-Based Approach to Address the Cold Start Problem in Collaborative Filtering for Personalized Movie Recommendation","authors":"Lasitha Uyangoda, S. Ahangama, Tharindu Ranasinghe","doi":"10.1109/ICDIM.2018.8847002","DOIUrl":"https://doi.org/10.1109/ICDIM.2018.8847002","url":null,"abstract":"A huge amount of user generated content related to movies is created with the popularization of web 2.0. With these continues exponential growth of data, there is an inevitable need for recommender systems as people find it difficult to make informed and timely decisions. Movie recommendation systems assist users to find the next interest or the best recommendation. In this proposed approach the authors apply the relationship of user feature-scores derived from user-item interaction via ratings to optimize the prediction algorithm’s input parameters used in the recommender system to improve the accuracy of predictions with less past user records. This addresses a major drawback in collaborative filtering, the cold start problem by showing an improvement of 8.4% compared to the base collaborative filtering algorithm. The user-feature generation and evaluation of the system is carried out using the ‘MovieLens 100k dataset’. The proposed system can be generalized to other domains as well.","PeriodicalId":120884,"journal":{"name":"2018 Thirteenth International Conference on Digital Information Management (ICDIM)","volume":"381 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115477323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ICDIM.2018.8847007
Muhammad Zaid Abrahams, J. Langerman
DevOps has become an emerging force within the Information Technology field in today’s development/operations climate. Information security within a DevOps environment has become a focal point for most organizations that have implemented the DevOps methodology and its principles. In most cases, the ability to secure a DevOps environment and the organization’s ability to adhere to, and comply with, industry specific standards, frameworks and best practice is an integral part of information security within a DevOps environment. This investigation aims to address those issues that may arise when an organization seeks to adhere to and comply with industry standards, frameworks and best practice in a manner that does not limit the velocity of the organization’s automated delivery/deployment pipeline. This study investigates this by collecting and analyzing industry and academic literature; and through a prototype demonstration, understanding technical compliance and its requirements within a DevOps environment, using existing industry tools and solutions.
{"title":"Compliance at Velocity within a DevOps Environment","authors":"Muhammad Zaid Abrahams, J. Langerman","doi":"10.1109/ICDIM.2018.8847007","DOIUrl":"https://doi.org/10.1109/ICDIM.2018.8847007","url":null,"abstract":"DevOps has become an emerging force within the Information Technology field in today’s development/operations climate. Information security within a DevOps environment has become a focal point for most organizations that have implemented the DevOps methodology and its principles. In most cases, the ability to secure a DevOps environment and the organization’s ability to adhere to, and comply with, industry specific standards, frameworks and best practice is an integral part of information security within a DevOps environment. This investigation aims to address those issues that may arise when an organization seeks to adhere to and comply with industry standards, frameworks and best practice in a manner that does not limit the velocity of the organization’s automated delivery/deployment pipeline. This study investigates this by collecting and analyzing industry and academic literature; and through a prototype demonstration, understanding technical compliance and its requirements within a DevOps environment, using existing industry tools and solutions.","PeriodicalId":120884,"journal":{"name":"2018 Thirteenth International Conference on Digital Information Management (ICDIM)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126597728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ICDIM.2018.8847020
Nora Madi, Hend Suliman Al-Khalifa
Grammatical error checking is a process of detecting and sometimes correcting erroneous words in a text. Various approaches have been used for detecting and correcting text in numerous languages. Techniques that have been used include rule-based, syntax-based, statistical-based, classification and neural networks. This paper presents previous works of Grammatical Error Correction or Detection systems, challenges associated with these systems, and, finally, suggested future directions.
{"title":"Grammatical Error Checking Systems: A Review of Approaches and Emerging Directions","authors":"Nora Madi, Hend Suliman Al-Khalifa","doi":"10.1109/ICDIM.2018.8847020","DOIUrl":"https://doi.org/10.1109/ICDIM.2018.8847020","url":null,"abstract":"Grammatical error checking is a process of detecting and sometimes correcting erroneous words in a text. Various approaches have been used for detecting and correcting text in numerous languages. Techniques that have been used include rule-based, syntax-based, statistical-based, classification and neural networks. This paper presents previous works of Grammatical Error Correction or Detection systems, challenges associated with these systems, and, finally, suggested future directions.","PeriodicalId":120884,"journal":{"name":"2018 Thirteenth International Conference on Digital Information Management (ICDIM)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129443824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ICDIM.2018.8846974
M. Koch, Hao Wang, Thomas Bäck
Using time series of on-board car data, this research focuses on predicting the damaged parts of a vehicle in a low speed crash by machine learning techniques. Based on a relatively small and class-imbalanced dataset, we present our automatic and for small datasets optimized method to use time series for machine learning. Based on 3982 extracted features, we are using feature selection algorithms to find the most significant ones for each component. We train random forest models per part with its most relevant set of features and optimize the hyper-parameters by different techniques. This so-called part-wise approach provides good insights into the model performance for each part and offers opportunities for optimizing the models. The final F1 prediction scores (reaching up to 94%) show the large potential of predicting damaged parts with on-board data only. Furthermore, for the worse performing parts of this small and imbalanced dataset, it indicates the potential for reaching good prediction scores when adding more training data. The utilization of such method offers great possibilities, e.g., in vehicle insurance processing for automatized settling of low speed crash damages.
{"title":"Machine Learning for Predicting the Damaged Parts of a Low Speed Vehicle Crash","authors":"M. Koch, Hao Wang, Thomas Bäck","doi":"10.1109/ICDIM.2018.8846974","DOIUrl":"https://doi.org/10.1109/ICDIM.2018.8846974","url":null,"abstract":"Using time series of on-board car data, this research focuses on predicting the damaged parts of a vehicle in a low speed crash by machine learning techniques. Based on a relatively small and class-imbalanced dataset, we present our automatic and for small datasets optimized method to use time series for machine learning. Based on 3982 extracted features, we are using feature selection algorithms to find the most significant ones for each component. We train random forest models per part with its most relevant set of features and optimize the hyper-parameters by different techniques. This so-called part-wise approach provides good insights into the model performance for each part and offers opportunities for optimizing the models. The final F1 prediction scores (reaching up to 94%) show the large potential of predicting damaged parts with on-board data only. Furthermore, for the worse performing parts of this small and imbalanced dataset, it indicates the potential for reaching good prediction scores when adding more training data. The utilization of such method offers great possibilities, e.g., in vehicle insurance processing for automatized settling of low speed crash damages.","PeriodicalId":120884,"journal":{"name":"2018 Thirteenth International Conference on Digital Information Management (ICDIM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128652571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ICDIM.2018.8847132
Soonsung Hwang, Jongpil Jeong, Youngbin Kang
Fault diagnosis of facility maintenance is very important. Unexpected equipment failures during the process lead to significant losses to the plant. In this paper, in order to detect defects and fault patterns, Support Vector Machine (SVM) which is one of the machine learning algorithms, classifies the data received from the equipment as normal or abnormal. After learning only normal data by using Restricted Boltzmann Machine (RBM). We propose a model to identify the data, and then we analyze the faults of facilities in real-time.
{"title":"SVM-RBM based Predictive Maintenance Scheme for IoT-enabled Smart Factory","authors":"Soonsung Hwang, Jongpil Jeong, Youngbin Kang","doi":"10.1109/ICDIM.2018.8847132","DOIUrl":"https://doi.org/10.1109/ICDIM.2018.8847132","url":null,"abstract":"Fault diagnosis of facility maintenance is very important. Unexpected equipment failures during the process lead to significant losses to the plant. In this paper, in order to detect defects and fault patterns, Support Vector Machine (SVM) which is one of the machine learning algorithms, classifies the data received from the equipment as normal or abnormal. After learning only normal data by using Restricted Boltzmann Machine (RBM). We propose a model to identify the data, and then we analyze the faults of facilities in real-time.","PeriodicalId":120884,"journal":{"name":"2018 Thirteenth International Conference on Digital Information Management (ICDIM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131280368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ICDIM.2018.8847052
Sansiri Tarnpradab, K. Hua
The prevalence of social media has made information sharing possible across the globe. The downside, unfortunately, is the wide spread of misinformation. Methods applied in most previous rumor classifiers give an equal weight, or attention, to words in the microblog, and do not take the context beyond microblog contents into account; therefore, the accuracy becomes plateaued. In this research, we propose an ensemble neural architecture to detect rumor on Twitter. The architecture incorporates word attention and context from the author to enhance the classification performance. In particular, the word-level attention mechanism enables the architecture to put more emphasis on important words when constructing the text representation. To derive further context, microblog posts composed by individual authors are exploited since they can reflect style and characteristics in spreading information, which are significant cues to help classify whether the shared content is rumor or legitimate news. The experiment on the real-world Twitter dataset collected from two well-known rumor tracking websites demonstrates promising results.
{"title":"Attention Based Neural Architecture for Rumor Detection with Author Context Awareness","authors":"Sansiri Tarnpradab, K. Hua","doi":"10.1109/ICDIM.2018.8847052","DOIUrl":"https://doi.org/10.1109/ICDIM.2018.8847052","url":null,"abstract":"The prevalence of social media has made information sharing possible across the globe. The downside, unfortunately, is the wide spread of misinformation. Methods applied in most previous rumor classifiers give an equal weight, or attention, to words in the microblog, and do not take the context beyond microblog contents into account; therefore, the accuracy becomes plateaued. In this research, we propose an ensemble neural architecture to detect rumor on Twitter. The architecture incorporates word attention and context from the author to enhance the classification performance. In particular, the word-level attention mechanism enables the architecture to put more emphasis on important words when constructing the text representation. To derive further context, microblog posts composed by individual authors are exploited since they can reflect style and characteristics in spreading information, which are significant cues to help classify whether the shared content is rumor or legitimate news. The experiment on the real-world Twitter dataset collected from two well-known rumor tracking websites demonstrates promising results.","PeriodicalId":120884,"journal":{"name":"2018 Thirteenth International Conference on Digital Information Management (ICDIM)","volume":" 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113949705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ICDIM.2018.8847094
A. Rizkiana, Hasrini Sari, P. Hardjomidjojo, B. Prihartono, I. Sunaryo, I. Prasetyo
Investor sentiment has a significant role in driving stock prices. Although many previous studies show that investor sentiment in social media can be used to predict stock price movements, there are two things that still need further investigation. The first one is related to the attention of investors that affect the ability to predict the movement of stocks price and its interaction with investor sentiment. The second one is related to the effect of the lead-lag relationship between investor sentiment, investor attention, and stock return. Therefore, the purpose of this research is to understand the effect of the lead-lag relationship between the three variables as well as the interaction between investor sentiment and investor attention in predicting the movement of stock prices. The steps taken to answer the research problem are to measure investor sentiment based on comments in social media Stockbit, measure investor attention based on search volume obtained from Google Trend, and then test the effect of lead-lag relationship and interaction between variable using Granger causality analysis and vector autoregression. Test results show that investor sentiment in Indonesia is a reaction from stock returns, not the cause, so it cannot be used to predict stock price movement. Also, investor attention measured by search volume in Google Trend cannot be used to predict stock price movement either. There are four reasons on why investor sentiment has no significant effect on stock return, which is the speed of information diffusion on the stock price, data source used, size of stock capitalization tested, and selection of investor sentiment measurement method. Furthermore, there are two reasons on why investor attention has no significant effect on stock return, which is related to stock capitalization size tested and google search volume that does not reflect investor attention. The insignificant effects of investor sentiment variable and investor attention to stock returns cause the interaction between the two not significant.
{"title":"Lead-Lag Relationship between Investor Sentiment in Social Media9 Investor Attention in Google, and Stock Return","authors":"A. Rizkiana, Hasrini Sari, P. Hardjomidjojo, B. Prihartono, I. Sunaryo, I. Prasetyo","doi":"10.1109/ICDIM.2018.8847094","DOIUrl":"https://doi.org/10.1109/ICDIM.2018.8847094","url":null,"abstract":"Investor sentiment has a significant role in driving stock prices. Although many previous studies show that investor sentiment in social media can be used to predict stock price movements, there are two things that still need further investigation. The first one is related to the attention of investors that affect the ability to predict the movement of stocks price and its interaction with investor sentiment. The second one is related to the effect of the lead-lag relationship between investor sentiment, investor attention, and stock return. Therefore, the purpose of this research is to understand the effect of the lead-lag relationship between the three variables as well as the interaction between investor sentiment and investor attention in predicting the movement of stock prices. The steps taken to answer the research problem are to measure investor sentiment based on comments in social media Stockbit, measure investor attention based on search volume obtained from Google Trend, and then test the effect of lead-lag relationship and interaction between variable using Granger causality analysis and vector autoregression. Test results show that investor sentiment in Indonesia is a reaction from stock returns, not the cause, so it cannot be used to predict stock price movement. Also, investor attention measured by search volume in Google Trend cannot be used to predict stock price movement either. There are four reasons on why investor sentiment has no significant effect on stock return, which is the speed of information diffusion on the stock price, data source used, size of stock capitalization tested, and selection of investor sentiment measurement method. Furthermore, there are two reasons on why investor attention has no significant effect on stock return, which is related to stock capitalization size tested and google search volume that does not reflect investor attention. The insignificant effects of investor sentiment variable and investor attention to stock returns cause the interaction between the two not significant.","PeriodicalId":120884,"journal":{"name":"2018 Thirteenth International Conference on Digital Information Management (ICDIM)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129786885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ICDIM.2018.8847000
Esther Gachanga, Michael W. Kimwele, L. Nderu
Sensitive information about individuals must not be revealed when sharing data, but a data set must remain useful for research and analysis when published. Anonymization methods have been considered as a possible solution for protecting the privacy of individuals. This is achieved by transforming data in a way that guarantees a certain degree of protection from re-identification threats. In the process, it is important to ensure that the quality of data is preserved. K-anonymity is the most commonly used approach for the anonymization of published datasets. However, the approach causes a decline in data utility. The key challenge for data publishers is how to anonymize data without causing a significant decline in data utility. The paper addresses this challenge by proposing a multidimensional mixed generalization. We conduct experiments with mixed generalization. Our results show that mixed generalization preserves the quality of data for classification.
{"title":"Sensitivity Based Anonymization with Multi-dimensional Mixed Generalization","authors":"Esther Gachanga, Michael W. Kimwele, L. Nderu","doi":"10.1109/ICDIM.2018.8847000","DOIUrl":"https://doi.org/10.1109/ICDIM.2018.8847000","url":null,"abstract":"Sensitive information about individuals must not be revealed when sharing data, but a data set must remain useful for research and analysis when published. Anonymization methods have been considered as a possible solution for protecting the privacy of individuals. This is achieved by transforming data in a way that guarantees a certain degree of protection from re-identification threats. In the process, it is important to ensure that the quality of data is preserved. K-anonymity is the most commonly used approach for the anonymization of published datasets. However, the approach causes a decline in data utility. The key challenge for data publishers is how to anonymize data without causing a significant decline in data utility. The paper addresses this challenge by proposing a multidimensional mixed generalization. We conduct experiments with mixed generalization. Our results show that mixed generalization preserves the quality of data for classification.","PeriodicalId":120884,"journal":{"name":"2018 Thirteenth International Conference on Digital Information Management (ICDIM)","volume":"17 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132835983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ICDIM.2018.8847044
Imran Rasheed, Vivek Gupta, H. Banka, C. Kumar
In the last decade, online content has entered a stage where news related organizations are reluctant to invest in offline operations due to excessive aberrations in content distributions. However, the proliferation of digital data in an unstructured or rather disordered form particularly for languages like Urdu has complicated the easy access to information. Consequently, the paper addresses the peculiarities of Urdu text classification of news origin. For this, the performance of the three classifiers such as Decision Tree (J48), Support Vector Machine (SVM) and k-nearest neighbor (KNN) was measured on the classification of Urdu text using WEKA (Waikato Environment Knowledge Analysis) tool. The assessment was carried out on a relatively large collection of Urdu text having over 16,678 documents containing mainly news articles from The Daily Roshni, an Urdu newspaper. Additionally, TF-IDF weighting scheme was used for feature selection and extraction of data. The Urdu text classification using SVM classifier performed quite better with promising accuracy and superior efficiency when compared to the other two classifiers. For this study, the dataset was formulated as per TRC (Text Retrieval Conference) community standard.
{"title":"Urdu Text Classification: A comparative study using machine learning techniques","authors":"Imran Rasheed, Vivek Gupta, H. Banka, C. Kumar","doi":"10.1109/ICDIM.2018.8847044","DOIUrl":"https://doi.org/10.1109/ICDIM.2018.8847044","url":null,"abstract":"In the last decade, online content has entered a stage where news related organizations are reluctant to invest in offline operations due to excessive aberrations in content distributions. However, the proliferation of digital data in an unstructured or rather disordered form particularly for languages like Urdu has complicated the easy access to information. Consequently, the paper addresses the peculiarities of Urdu text classification of news origin. For this, the performance of the three classifiers such as Decision Tree (J48), Support Vector Machine (SVM) and k-nearest neighbor (KNN) was measured on the classification of Urdu text using WEKA (Waikato Environment Knowledge Analysis) tool. The assessment was carried out on a relatively large collection of Urdu text having over 16,678 documents containing mainly news articles from The Daily Roshni, an Urdu newspaper. Additionally, TF-IDF weighting scheme was used for feature selection and extraction of data. The Urdu text classification using SVM classifier performed quite better with promising accuracy and superior efficiency when compared to the other two classifiers. For this study, the dataset was formulated as per TRC (Text Retrieval Conference) community standard.","PeriodicalId":120884,"journal":{"name":"2018 Thirteenth International Conference on Digital Information Management (ICDIM)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114439676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：