Pub Date : 2017-08-31DOI: 10.14257/ijdta.2017.10.8.10
A. Octavian, Marsetio, B. Yulianto, Hari Utomo, M. Madjid, Susaningtyas Nefo Handayani Kertopati
Colonialism has been a preliminary thesis that can be addressed in the Indonesian maritime culture degradation. In order to restore the maritime culture, the current representation of degradation in the community level needs to be considered. This paper provides the historical process of Banten maritime culture degradation and the existing condition of degradation itself in the context of sea social practice on sociological perspective.
{"title":"Maritime Culture Degradation: History, Identity, and Social Practice of Seafaring in Banten","authors":"A. Octavian, Marsetio, B. Yulianto, Hari Utomo, M. Madjid, Susaningtyas Nefo Handayani Kertopati","doi":"10.14257/ijdta.2017.10.8.10","DOIUrl":"https://doi.org/10.14257/ijdta.2017.10.8.10","url":null,"abstract":"Colonialism has been a preliminary thesis that can be addressed in the Indonesian maritime culture degradation. In order to restore the maritime culture, the current representation of degradation in the community level needs to be considered. This paper provides the historical process of Banten maritime culture degradation and the existing condition of degradation itself in the context of sea social practice on sociological perspective.","PeriodicalId":13926,"journal":{"name":"International journal of database theory and application","volume":"43 1","pages":"99-114"},"PeriodicalIF":0.0,"publicationDate":"2017-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74531986","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 : 2017-08-31DOI: 10.14257/IJDTA.2017.10.8.02
B. Devi, V. N. Mandhala, D. Bhattacharyya, Hye-jin Kim
Innovations in the sector of information technology have enabled the collection and processing of enormous amounts of spatial data. The goal of data mining is to determine nuggets. Spatial data mining identifies the collocation rules. Spatial data are considered from the spatial objects. The considered spatial data is preprocessed by using the data mining tool. To the preprocessed data, collocation rule is applied for detecting the frequent item sets. Disaster impacted areas were predicted by applying the collocation rule. In particular to spatial data mining, when spatial data are comparatively represented in time series, a spatio-temporal significance is concluded. In this perspective, the collocation rule that is an epitome for the spatial data acquires changes with temporal impact. Therefore, the changes that arise to the spatial knowledge are the spatio-temporal transactions. Extracting the spatio-temporal transactions and finding the various behavioral aspects of collocation is one of the considerable activities of GIS. By implementing the collocation rule with “nearby” as the predicate, disaster affected areas are identified follows the representation of the spatial data on Geographical Information Systems (GIS) by various colored pinpoints for all the quarters of a year. From that, the regions at risk zone of disaster were predicted, then the analyzed spatial data will be redirected to the health organizations for supervising campaigns. Our focus is to forecast the disaster, design the spatio-temporal trees for all the quarters of a year and to represent the spatial nuggets on GIS. Therefore, a spatio-temporal disaster management system is designed and implemented. A novel data structure for the spatio-temporal data is proposed.
{"title":"An Intelligible Illustration of an Epidemic Spatio – Temporal Statistics on GIS","authors":"B. Devi, V. N. Mandhala, D. Bhattacharyya, Hye-jin Kim","doi":"10.14257/IJDTA.2017.10.8.02","DOIUrl":"https://doi.org/10.14257/IJDTA.2017.10.8.02","url":null,"abstract":"Innovations in the sector of information technology have enabled the collection and processing of enormous amounts of spatial data. The goal of data mining is to determine nuggets. Spatial data mining identifies the collocation rules. Spatial data are considered from the spatial objects. The considered spatial data is preprocessed by using the data mining tool. To the preprocessed data, collocation rule is applied for detecting the frequent item sets. Disaster impacted areas were predicted by applying the collocation rule. In particular to spatial data mining, when spatial data are comparatively represented in time series, a spatio-temporal significance is concluded. In this perspective, the collocation rule that is an epitome for the spatial data acquires changes with temporal impact. Therefore, the changes that arise to the spatial knowledge are the spatio-temporal transactions. Extracting the spatio-temporal transactions and finding the various behavioral aspects of collocation is one of the considerable activities of GIS. By implementing the collocation rule with “nearby” as the predicate, disaster affected areas are identified follows the representation of the spatial data on Geographical Information Systems (GIS) by various colored pinpoints for all the quarters of a year. From that, the regions at risk zone of disaster were predicted, then the analyzed spatial data will be redirected to the health organizations for supervising campaigns. Our focus is to forecast the disaster, design the spatio-temporal trees for all the quarters of a year and to represent the spatial nuggets on GIS. Therefore, a spatio-temporal disaster management system is designed and implemented. A novel data structure for the spatio-temporal data is proposed.","PeriodicalId":13926,"journal":{"name":"International journal of database theory and application","volume":"2676 1","pages":"11-20"},"PeriodicalIF":0.0,"publicationDate":"2017-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79768413","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 : 2017-08-31DOI: 10.14257/IJDTA.2017.10.8.07
Gap-Jun Son, Yun-Hee Son, Kyu-Chul Lee
{"title":"Development of Ontology Engine for Interoperability of L-V-C Integrating System","authors":"Gap-Jun Son, Yun-Hee Son, Kyu-Chul Lee","doi":"10.14257/IJDTA.2017.10.8.07","DOIUrl":"https://doi.org/10.14257/IJDTA.2017.10.8.07","url":null,"abstract":"","PeriodicalId":13926,"journal":{"name":"International journal of database theory and application","volume":"87 1","pages":"71-82"},"PeriodicalIF":0.0,"publicationDate":"2017-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81013221","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 : 2017-08-31DOI: 10.14257/ijdta.2017.10.8.04
Young-Shing Youn, Hye-Jeong Song, Chan-Young Park, Jong-Dae Kim, Yu-Seop Kim
Semantic Role Labeling (SRL) is to determine the relationship between predicates and their arguments in a sentence. In order to determine the semantic roles, a large amount of corpus with annotated semantic roles is required. Nowadays the most widely used semantic corpus is Proposition Bank (PropBank) which is semantically annotated over the predicate and argument structure. But the Korean version of the PropBank could not be widely used because the corpus has limitation in size and be different from its original English version in its usability. To solve these problems, we also used another semantic tagged corpus, built by Sejong Plan, which is nation-wide Korean corpus construction project. However, the task of corpus construction with semantic roles defined in PropBank and Sejong is much time-consuming and these corpora use their own role sets. They finally require a way of converting one role to other side role(s). In this paper, we propose a method for automatically converting the roles. First, we use similarity between a given noun argument word to find a new role and noun words appearing in the example sentences of candidate roles. Second, we extract suffix of the argument word and estimate closeness between the suffix and candidate roles. Finally, the predicate itself is used for selection,that is we calculate the closeness between the predicate and the candidate roles. With these, the role is decided among multiple candidate roles. In the experiment, we convert 491 arguments automatically and about 78% of them show the agreement with manually annotated arguments.
语义角色标注(Semantic Role Labeling, SRL)是用来确定句子中谓语及其参数之间的关系。为了确定语义角色，需要大量带有标注语义角色的语料库。目前使用最广泛的语义语料库是命题库(PropBank)，它对谓词和论证结构进行了语义标注。但韩国版的PropBank由于语料库规模有限，而且在可用性方面与英文原版存在差异，因此未能得到广泛应用。为了解决这些问题，我们还使用了另一个语义标记语料库，该语料库是由Sejong Plan建立的，这是一个全国性的韩国语语料库建设项目。然而，使用PropBank和Sejong中定义的语义角色构建语料库的任务非常耗时，并且这些语料库使用自己的角色集。它们最后需要一种将一个角色转换为另一个角色的方法。本文提出了一种自动转换角色的方法。首先，我们利用给定的名词论证词与候选角色例句中出现的名词词之间的相似性来寻找新角色。其次，我们提取参数词的后缀，并估计后缀与候选角色之间的接近度。最后，谓词本身用于选择，也就是说，我们计算谓词和候选角色之间的接近度。有了这些，在多个候选角色中决定角色。在实验中，我们自动转换了491个参数，其中约78%的参数与人工标注的参数一致。
{"title":"Role Conversion Considering Its Context and Syntactic Property","authors":"Young-Shing Youn, Hye-Jeong Song, Chan-Young Park, Jong-Dae Kim, Yu-Seop Kim","doi":"10.14257/ijdta.2017.10.8.04","DOIUrl":"https://doi.org/10.14257/ijdta.2017.10.8.04","url":null,"abstract":"Semantic Role Labeling (SRL) is to determine the relationship between predicates and their arguments in a sentence. In order to determine the semantic roles, a large amount of corpus with annotated semantic roles is required. Nowadays the most widely used semantic corpus is Proposition Bank (PropBank) which is semantically annotated over the predicate and argument structure. But the Korean version of the PropBank could not be widely used because the corpus has limitation in size and be different from its original English version in its usability. To solve these problems, we also used another semantic tagged corpus, built by Sejong Plan, which is nation-wide Korean corpus construction project. However, the task of corpus construction with semantic roles defined in PropBank and Sejong is much time-consuming and these corpora use their own role sets. They finally require a way of converting one role to other side role(s). In this paper, we propose a method for automatically converting the roles. First, we use similarity between a given noun argument word to find a new role and noun words appearing in the example sentences of candidate roles. Second, we extract suffix of the argument word and estimate closeness between the suffix and candidate roles. Finally, the predicate itself is used for selection,that is we calculate the closeness between the predicate and the candidate roles. With these, the role is decided among multiple candidate roles. In the experiment, we convert 491 arguments automatically and about 78% of them show the agreement with manually annotated arguments.","PeriodicalId":13926,"journal":{"name":"International journal of database theory and application","volume":"82 1","pages":"31-42"},"PeriodicalIF":0.0,"publicationDate":"2017-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84721529","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 : 2017-08-31DOI: 10.14257/ijdta.2017.10.8.03
Jung-Jae Kim, Min-Woo Ryu, S. Cha, Kuk-Hyun Cho
The classification problem is one of most important problems in Artificial Intelligence (AI) Research. Classification is used in various fields such as speech recognition, image classification, word prediction in text. Deep Neural Network (DNN) is the most commonly used for the classification. However, DNN requires a lot of learning time because of its deep network structure and lots of data. At this time, if a new feature or a new category class (new data) is added, the existing data on which learning has been completed is also re-learned. And the same learning time (very long time) as the previous learning time is needed. Therefore, in this paper, we proposes Weight Initialization-based Partial Training (WIPT) algorithm, that decompose the existing weight matrix through Singular Value Decomposition (SVD) and generate a latent matrix with information learned by the existing model. In order to increase the learning efficiency, we use a strategy of learning new features or classes by initializing newly added weights to appropriate values. Finally we verify the efficiency of the proposed algorithm by comparing it with the existing whole learning.
{"title":"Weight Initialization based Partial Training Algorithm for Fast Learning in Neural Network","authors":"Jung-Jae Kim, Min-Woo Ryu, S. Cha, Kuk-Hyun Cho","doi":"10.14257/ijdta.2017.10.8.03","DOIUrl":"https://doi.org/10.14257/ijdta.2017.10.8.03","url":null,"abstract":"The classification problem is one of most important problems in Artificial Intelligence (AI) Research. Classification is used in various fields such as speech recognition, image classification, word prediction in text. Deep Neural Network (DNN) is the most commonly used for the classification. However, DNN requires a lot of learning time because of its deep network structure and lots of data. At this time, if a new feature or a new category class (new data) is added, the existing data on which learning has been completed is also re-learned. And the same learning time (very long time) as the previous learning time is needed. Therefore, in this paper, we proposes Weight Initialization-based Partial Training (WIPT) algorithm, that decompose the existing weight matrix through Singular Value Decomposition (SVD) and generate a latent matrix with information learned by the existing model. In order to increase the learning efficiency, we use a strategy of learning new features or classes by initializing newly added weights to appropriate values. Finally we verify the efficiency of the proposed algorithm by comparing it with the existing whole learning.","PeriodicalId":13926,"journal":{"name":"International journal of database theory and application","volume":"75 1","pages":"21-30"},"PeriodicalIF":0.0,"publicationDate":"2017-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83382825","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 : 2017-07-31DOI: 10.14257/ijdta.2017.10.7.08
K. Joo, Ji-Hoon Seo, N. Park
As various forms of big data, which includes but not limited to, large volume texts, voice data and videos, are being accumulated whilst the waves of the information age are accelerating progressively, the number of inter-disciplinary analysis solutions with capabilities to use such information is increasing, and accordingly, the developments, such as the drop of costs required for data storage and various Social Network Services, have brought forth the quantitate and qualitative stretch of the data. The phenomenon makes it possible to achieve the types of data usage which were not available in the past, and thus the potential values and leverage of data are on the rise. Studies that that apply such inter-disciplinary analysis system for the improvement of the educational system to suggest future-oriented education system are being carried out at progressive levels. This study has carried out an analysis on big data with Twitter as its subject and suggested, via the natural language process of data and frequency analysis, the quantitative scale indicative of how various issues and performances relating to creative education in South Korea have been handled.
{"title":"Analysis on Big Data by Performance Factors of Creative Education using Semi-structured Data-based Twitter","authors":"K. Joo, Ji-Hoon Seo, N. Park","doi":"10.14257/ijdta.2017.10.7.08","DOIUrl":"https://doi.org/10.14257/ijdta.2017.10.7.08","url":null,"abstract":"As various forms of big data, which includes but not limited to, large volume texts, voice data and videos, are being accumulated whilst the waves of the information age are accelerating progressively, the number of inter-disciplinary analysis solutions with capabilities to use such information is increasing, and accordingly, the developments, such as the drop of costs required for data storage and various Social Network Services, have brought forth the quantitate and qualitative stretch of the data. The phenomenon makes it possible to achieve the types of data usage which were not available in the past, and thus the potential values and leverage of data are on the rise. Studies that that apply such inter-disciplinary analysis system for the improvement of the educational system to suggest future-oriented education system are being carried out at progressive levels. This study has carried out an analysis on big data with Twitter as its subject and suggested, via the natural language process of data and frequency analysis, the quantitative scale indicative of how various issues and performances relating to creative education in South Korea have been handled.","PeriodicalId":13926,"journal":{"name":"International journal of database theory and application","volume":"31 1","pages":"89-101"},"PeriodicalIF":0.0,"publicationDate":"2017-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78253230","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 : 2017-07-31DOI: 10.14257/ijdta.2017.10.7.10
Se-Hoon Jung, Jong-Chan Kim, Chun-Bo Sim
We propose a conduct mobile cloud situation service with using Google App Engine based on PaaS in order to get situation service in various mobile devices without any subordination to any specific platform. At the same time, it is intended to shorten the situation service reasoning time with mapping the regular reasoning of SWRL to JESS reasoning engine by connecting the values such as Class, Property and Individual which are regular information in the form of SWRL to Jess reasoning engine via JESSTab plug-in in order to overcome the demerit of queries reasoning method of SparQL in semantic search which is a previous reasoning method.
{"title":"A Study on Efficiency Improvement of Situation Data Deduction using Semantic Web Rule Language and JESS based on PaaS Cloud","authors":"Se-Hoon Jung, Jong-Chan Kim, Chun-Bo Sim","doi":"10.14257/ijdta.2017.10.7.10","DOIUrl":"https://doi.org/10.14257/ijdta.2017.10.7.10","url":null,"abstract":"We propose a conduct mobile cloud situation service with using Google App Engine based on PaaS in order to get situation service in various mobile devices without any subordination to any specific platform. At the same time, it is intended to shorten the situation service reasoning time with mapping the regular reasoning of SWRL to JESS reasoning engine by connecting the values such as Class, Property and Individual which are regular information in the form of SWRL to Jess reasoning engine via JESSTab plug-in in order to overcome the demerit of queries reasoning method of SparQL in semantic search which is a previous reasoning method.","PeriodicalId":13926,"journal":{"name":"International journal of database theory and application","volume":"10 1","pages":"113-122"},"PeriodicalIF":0.0,"publicationDate":"2017-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89164515","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 : 2017-07-31DOI: 10.14257/IJDTA.2017.10.7.04
M. Edison, A. Aloysius
Sentiment Analysis plays a vital role in the domain of Big Data. Especially, Sentiment Analysis is the process to determine the text based analysis. Particularly, Twitter social media network allows 140 characters for text limitation. So people can convey their emotions by using emoticons, proper and improper text. Improper text is named as acronyms, the acronyms and emoticons are the greatest challenging issues for classifying and evaluating the opinions. The issues like sentiments, acronyms and emoticons have distinct meaning. So they are isolated. Then the classified emotions could be formulated in different classes like positive, negative and neutral emotions. In this paper, a new algorithm named Senti_Acron which has been proposed to detect the polarity and classify the different classes. The acronyms and emoticons have matched with Synset and SemEval dictionary words and extract the semantic words from the data set. Whereas, the features are selected with a help of equations to measure the frequent occurrences of a sentiment and assigned ranking for the sentiment based on the occurrences. The result of the proposed work Senti_Acron is 0.6875, in percentage 68.75% which provides enhanced accuracy.
{"title":"Lexicon based Acronyms and Emoticons Classification of Sentiment Analysis (SA) on Big Data","authors":"M. Edison, A. Aloysius","doi":"10.14257/IJDTA.2017.10.7.04","DOIUrl":"https://doi.org/10.14257/IJDTA.2017.10.7.04","url":null,"abstract":"Sentiment Analysis plays a vital role in the domain of Big Data. Especially, Sentiment Analysis is the process to determine the text based analysis. Particularly, Twitter social media network allows 140 characters for text limitation. So people can convey their emotions by using emoticons, proper and improper text. Improper text is named as acronyms, the acronyms and emoticons are the greatest challenging issues for classifying and evaluating the opinions. The issues like sentiments, acronyms and emoticons have distinct meaning. So they are isolated. Then the classified emotions could be formulated in different classes like positive, negative and neutral emotions. In this paper, a new algorithm named Senti_Acron which has been proposed to detect the polarity and classify the different classes. The acronyms and emoticons have matched with Synset and SemEval dictionary words and extract the semantic words from the data set. Whereas, the features are selected with a help of equations to measure the frequent occurrences of a sentiment and assigned ranking for the sentiment based on the occurrences. The result of the proposed work Senti_Acron is 0.6875, in percentage 68.75% which provides enhanced accuracy.","PeriodicalId":13926,"journal":{"name":"International journal of database theory and application","volume":"10 1","pages":"41-54"},"PeriodicalIF":0.0,"publicationDate":"2017-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83472659","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 : 2017-07-31DOI: 10.14257/IJDTA.2017.10.7.09
Sanghyun (Hugh) Kim, Joo-Yung Kim, Yiseul Kwon, Sungjin Jung, Eunju Park, Hankyu Lim
While the widespread use of smart devices has led to the development of various applications in our daily lives, there are not many travel applications for an area called Andong. For this reason, we designed and implemented ‘an application, which provides information on culture and tourism in Andong’. We implemented voice recognition function and GPS-based position information function in the application to provide travellers visiting Andong with accurate information about the area, and to improve user convenience for those who are not familiar with the device. It is believed that the application will provide travelers and citizens in Andong with accurate information and convenient access to the information, as well as more choices for application.
{"title":"Design and Implementation for Applications That Provide Andong Culture and Tourism Information","authors":"Sanghyun (Hugh) Kim, Joo-Yung Kim, Yiseul Kwon, Sungjin Jung, Eunju Park, Hankyu Lim","doi":"10.14257/IJDTA.2017.10.7.09","DOIUrl":"https://doi.org/10.14257/IJDTA.2017.10.7.09","url":null,"abstract":"While the widespread use of smart devices has led to the development of various applications in our daily lives, there are not many travel applications for an area called Andong. For this reason, we designed and implemented ‘an application, which provides information on culture and tourism in Andong’. We implemented voice recognition function and GPS-based position information function in the application to provide travellers visiting Andong with accurate information about the area, and to improve user convenience for those who are not familiar with the device. It is believed that the application will provide travelers and citizens in Andong with accurate information and convenient access to the information, as well as more choices for application.","PeriodicalId":13926,"journal":{"name":"International journal of database theory and application","volume":"38 1","pages":"102-112"},"PeriodicalIF":0.0,"publicationDate":"2017-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90769308","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 : 2017-07-31DOI: 10.14257/IJDTA.2017.10.7.01
K. Bhuvaneswari, R. Parimala
In recent years there has been a steady increase in interest from brands, companies and researchers in Sentiment Analysis and its application to business analytics. It is the process of determining the emotional tone behind a series of words, used to gain an understanding of the attitudes, opinions and emotions expressed within an online mention. Sentiment analysis is a feature of text analysis and natural language processing (NLP) research that is increasingly growing in popularity as a multitude of use-cases emerges. Lexicon based and Machine learning is the two methods used for analysis the sentiments from the content. The proposed feature selection model Ssentiment Reviews Classification using Hybrid Feature Selection (SRCHFS) that extract synsets feature set coupled with Correlation feature selection method can improve the performance of sentiment classification. Nouns, verbs, adjectives and adverbs are organized into synsets, each representing one underlying lexical concept. A set of cognitive synsets is selected using WordNet based POS (Part Of Speech). Support Vector Machine (SVM) classifier is used for sentiment classification on a data set of Movie reviews, Multi Domain product reviews, Amazon Cell phone reviews and Yelp Restaurant reviews. The experimental outcome might result into better accuracy with the existing studies.
{"title":"Sentiment Reviews Classification using Hybrid Feature Selection","authors":"K. Bhuvaneswari, R. Parimala","doi":"10.14257/IJDTA.2017.10.7.01","DOIUrl":"https://doi.org/10.14257/IJDTA.2017.10.7.01","url":null,"abstract":"In recent years there has been a steady increase in interest from brands, companies and researchers in Sentiment Analysis and its application to business analytics. It is the process of determining the emotional tone behind a series of words, used to gain an understanding of the attitudes, opinions and emotions expressed within an online mention. Sentiment analysis is a feature of text analysis and natural language processing (NLP) research that is increasingly growing in popularity as a multitude of use-cases emerges. Lexicon based and Machine learning is the two methods used for analysis the sentiments from the content. The proposed feature selection model Ssentiment Reviews Classification using Hybrid Feature Selection (SRCHFS) that extract synsets feature set coupled with Correlation feature selection method can improve the performance of sentiment classification. Nouns, verbs, adjectives and adverbs are organized into synsets, each representing one underlying lexical concept. A set of cognitive synsets is selected using WordNet based POS (Part Of Speech). Support Vector Machine (SVM) classifier is used for sentiment classification on a data set of Movie reviews, Multi Domain product reviews, Amazon Cell phone reviews and Yelp Restaurant reviews. The experimental outcome might result into better accuracy with the existing studies.","PeriodicalId":13926,"journal":{"name":"International journal of database theory and application","volume":"28 1","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2017-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89488619","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：