I-hsien Ting | National University of Kaohsiung (original) (raw)

Papers by I-hsien Ting

Communications in Computer and Information Science, 2014

The rise of Social Networking Services (SNSs) has not only transformed people as well as consumer... more The rise of Social Networking Services (SNSs) has not only transformed people as well as consumer behavior on the Internet, but also transformed the means by which various enterprises globally conduct their promotional and marketing campaigns. There are a variety of means by which enterprises have launched their marketing campaigns on Social Networking Services, and one of the most common techniques adopted is through extensive advertising campaigns on SNSs. This study seeks to examine consumer behaviors towards advertisements on Social Networking Services. Key factors affecting consumer behaviors include usage pattern, the credibility of a particular Social Networking Service as well as electronic word-of-mouth. This clearly illustrates that in today’s virtual electronic world, social media have progressed from being merely a place to meet people, to being a virtual sales floor. It is unexpected that consumer behaviors are influenced by the electronic word-of-mouth of friends rather than that of strangers.

Journal of Intelligent & Fuzzy Systems, 2014

Growing popularity of social networking not only brings the convenience of information sharing bu... more Growing popularity of social networking not only brings the convenience of information sharing but also concerns of privacy breaches. Information on social networks can be modeled as un-weighted or weighted graph data. To preserve privacy, k-anonymity on relational, set-valued, and graph data have been studied extensively in recent years. In this work, we consider the edge weight anonymity problem. In particular, to protect the weight privacy of the shortest path between two vertices on a weighted graph, we present a new concept called k-anonymous path privacy. A published social network graph with k-anonymous path privacy has at least k indistinguishable shortest paths between the source and destination vertices. Three greedy-based modification algorithms, based on modifying different types of edges, to achieve k-anonymous path privacy are proposed. Experimental results showing the feasibility and characteristics of the proposed approach are presented. The proposed techniques clearly provide different options to achieve the same level of privacy under different requirements.

Proceedings of the The 3rd Multidisciplinary International Social Networks Conference on SocialInformatics 2016, Data Science 2016, 2016

Opinion mining is a very hot and important issue of social media related researches, due to it is... more Opinion mining is a very hot and important issue of social media related researches, due to it is helpful for understanding the opinion of users in social media. In our previous research, we have already developed an approach to detect an important effect, which is called "Spiral of Silence (SoS)". The approach is developed based on opinion mining and sentimental analysis. In this paper, we will use the approach to test related issues of SoS in social medias and try to understand the difference between these social media platforms. Analysis results are also presented in the paper as well as discussions.

J. Univers. Comput. Sci., 2012

With the rapid growth of Internet and social networking websites, various services are provided i... more With the rapid growth of Internet and social networking websites, various services are provided in these platforms. For instance, Facebook focuses on social activities, Twitter and Plurk (which are called microblogs) are both focusing on the interaction of users through short messages. Millions of users enjoy services from these websites which are full of marketing possibilities. Understanding the users can assist companies to enhance the accuracy and efficiency of the target market. In this paper, a social recommendation system based on the data from microblogs is proposed. This social recommendation system is built according to the messages and social structure of target users. The similarity of the discovered features of users and products will then be calculated as the essence of the recommendation engine. A case study included in the paper presents how the recommendation system works based on real data from Plurk.

J. Web Eng., 2016

Privacy-preserving computation has recently attracted much attention in areas of transaction, soc... more Privacy-preserving computation has recently attracted much attention in areas of transaction, social networking, location-based, and mobile services. The inexpensive storage and efficient computation of cloud computing technology is expected to further escalate these services to a higher and wider level, without compromising the breaches of sensitive information. In this work, we study the shortest path distance computing in the cloud while preserving two types of privacy in the same time: k-neighborhood privacy and sensitive path privacy. We propose a new privacy model called (k, p)-shortest path neighborhood privacy, which is an extension of [19] and more flexible than 1-neighborhood-d-radius model. We also develop an efficient four-step shortest distance computation scheme to achieve (k, p)-shortest path neighborhood privacy on p outsourced servers in the cloud, which combines the construction of k-skip shortest path sub-graphs, sensitive vertex adjustment, vertex hierarchy labeling and bottom-up partitioning techniques. Numerical experiments show that the proposed approach is more efficient than prior model of constructing the 1-neighborhood privacy graph and also requires less querying time.

2017 International Conference on Behavioral, Economic, Socio-cultural Computing (BESC), 2017

In recent years, users are widely intend to express and share their opinions over the Internet. H... more In recent years, users are widely intend to express and share their opinions over the Internet. However, due to the characters of social media, it appears negative use of social media. Cyberbullying is one of the abuse behavior in the Internet as well as a very serious social problem. Under this background and motivation, it can help to prevent the happen of cyberbullying if we can develop relevant techniques to discover cyberbullying in social media. Thus, in this paper we propose an approach based on social networks analysis and data mining for cyberbullying detection. In the approach, there are three main techniques for cyberbullying discovery will be studied, including keyword matching technique, opinion mining and social network analysis. In addition to the approach, we will also discuss the experimental design for the evaluation of the performance.

2011 International Conference on Advances in Social Networks Analysis and Mining, 2011

2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, 2012

2013 IEEE International Conference on Systems, Man, and Cybernetics, 2013

ABSTRACT Preserving privacy in social networking environment has been studied extensively in rece... more ABSTRACT Preserving privacy in social networking environment has been studied extensively in recent years. Although more works have adopted un-weighted graphs to model network relationships, weighted graph modeling can provide deeper analysis of the degree of relationships. Previous works on weighted graph privacy have concentrated on preserving the shortest path characteristic between pairs of vertices. Two common types of privacy have been proposed. One type of privacy tried to add random noise edge weights to the graph but still maintain the same shortest path. The other privacy, k-shortest path privacy, minimally perturbed edge weights so that there exist k shortest paths. However, the k-shortest path privacy did not consider degree attacks on the nodes of anonymized shortest paths. For example, if the adversary possesses background knowledge of node degrees on the shortest path, the true shortest path can be identified. In this work, we present a new concept called (k1, k2)-shortest path privacy to prevent such privacy breach. A published network graph with (k1, k2)-shortest path privacy has at least k1 indistinguishable shortest paths between the source and destination vertices. In addition, for the non-overlapping vertices on the k1 shortest paths, there exist at least k2 vertices with same node degree and lie on more than one shortest path. Three heuristic algorithms are proposed and experimental results showing the feasibility and characteristics of the proposed approaches are presented.

Proceedings of International Conference on Information Integration and Web-based Applications & Services - IIWAS '13, 2013

ABSTRACT Efficient shortest path calculation has been studied extensively, in particular, in the ... more ABSTRACT Efficient shortest path calculation has been studied extensively, in particular, in the distributed environment. However, preserving privacy in the cloud environment has just attracted latest attention. To preserve fixed-pattern one-neighborhood privacy in the cloud, current approach requires the calculation of all-pairs shortest paths in advance, which is time consuming for large graphs. In addition, specific paths that are sensitive and require hiding the source and destination vertices are not well addressed. In this work, we propose a new flexible k-neighborhood privacy-protection and efficient shortest distance computation scheme for sensitive shortest paths in the cloud environment. Combining the construction of k-skip shortest path sub-graphs, sensitive vertex adjustment, vertex hierarchy labeling and bottom-up partitioning techniques, the proposed approach not only subsumes one-neighborhood privacy but also provides efficient partitioning and query processing for sensitive shortest paths. Numerical experiments demonstrating the characteristics of proposed approach are presented.

Springer Proceedings in Complexity, 2013

The explosive growth of the Internet has made information on the web large and complicated. If th... more The explosive growth of the Internet has made information on the web large and complicated. If the structure of a website is not optimized, users could easily get lost and could not find the most important information at the first time. The adaptive website can present the information that users needed by analyzing the users’ behavior. However, visitors may have different needs at different times. Most of recommended methods are not considerate of dynamic or time-dependent needs. This paper presents a recommender system based on reinforcement learning. We assume that five parameters are on recommendation, which include clicks of the page, time that spent on viewing the page, paths to find the page, hierarchy of the page, and the rank of the page. With the help of reinforcement learning to adjust the weight of five parameters, we aim to reduce the paths that user needed to find the object page.

Springer Proceedings in Complexity, 2013

Privacy preserving network publishing has been studied extensively in recent years. Although more... more Privacy preserving network publishing has been studied extensively in recent years. Although more works have adopted un-weighted graphs to model network relationships, weighted graph modeling can provide deeper analysis of the degree of relationships. Previous works on weighted graph privacy have concentrated on preserving the shortest path characteristic between pairs of vertices. Two common types of privacy have been proposed. One type of privacy tried to add random noise edge weights to the graph but still maintain the same shortest path. The other privacy, k-shortest path privacy, minimally perturbed edge weights so that there exist k shortest paths. However, the k-shortest path privacy did not consider degree attacks on the nodes of anonymized shortest paths. For example, if the adversary possesses background knowledge of node degrees on the shortest path, the true shortest path can be identified. We have previously presented a new concept called (k 1 , k 2 )-shortest path privacy to prevent such privacy breach [1]. A published network graph with (k 1 , k 2 )-shortest path privacy has at least k 1 indistinguishable shortest paths between the source and destination vertices. In addition, for the non-overlapping vertices on the k 1 shortest paths, there exist at least k 2 vertices with same node degree and lie on more than one shortest path. In this work, we further propose edge insertion and edge weight determination techniques to effectively achieve the proposed privacy. Numerical comparisons based on average clustering coefficient and average shortest path length show that the proposed TNF approach is simple and effective.

Springer Proceedings in Complexity, 2013

In recent years, with the growth of social networking websites, users are very active in these pl... more In recent years, with the growth of social networking websites, users are very active in these platforms and a large amount of data is aggregated. Among those social networking websites, Facebook is the most popular one that has most users. However, in Facebook, the existence of Hate Groups is a very critical issue with the problem of abusing. Therefore, many researchers are devoting themselves to detecting the potential hate groups, using the techniques of social networks analysis and web mining. In this paper, we will propose an approach based on the techniques of social networks analysis and web mining to detect the potential hate groups. The data from Facebook are being processed. In the research, hate groups for 3C are selected as the training data. The social network structures and keywords of these groups will be treated as the features which will be used for discovering the potential hate groups in Facebook.

Lecture Notes in Computer Science, 2011

2011 Second International Conference on Innovations in Bio-inspired Computing and Applications, 2011

Springer Proceedings in Complexity, 2013

International Journal of Data Warehousing and Mining, 2013

Location and local service is one of the hottest bunches of applications in recent years, due to ... more Location and local service is one of the hottest bunches of applications in recent years, due to the proliferation of Global Position System (GPS) and mobile web search technology. Spatial queries retrieving neighboring Point-Of-Interests (POI) require actual user locations for services. However, exposing the physical location of querier to service system may pose privacy threat to users, if malicious adversary has access to the system. To hinder the service system from obtaining the “true” location of querier, current obfuscation-based approach requires a trusted third party anonymizer. As for the data-encryption-based and cPIR-based approaches, they incur costly computation overheads. Although the secure hardware-aided PIR-based technique has been shown to be superior to formers, it did not consider the characteristics of data distribution of searching domain. To deal with the problem of non-uniform data distribution and efficient retrieval, we propose four schemes: MSQL, NSQL, MN...

2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2012

ABSTRACT Due to the proliferation of Global Position System (GPS) and smart phone technology, Loc... more ABSTRACT Due to the proliferation of Global Position System (GPS) and smart phone technology, Location-Based Service (LBS) has attained tremendous growth in recent years. Spatial queries retrieving nearest Point-Of-Interests (POI) require actual user locations for services. However, sharing such sensitive personal location information with potentially malicious servers may cause concerns about user privacy. The current obfuscation-based approach addressing this problem cannot provide binding privacy guarantees as a trusted third-party anonymizer is required. On the other hand, the data-encryption-based and cPIR-based approaches incur costly computation overheads. Recently, the secure hardware-aided PIR-based technique has been shown to be superior to formers, but it did not consider the characteristics of data distribution of searching domain. In this work, we propose two schemes: MSQL, NSQL, based on flexible multi-layer grids and non-empty lookup table for efficient storage and retrieval on non-uniform distribution of POI data, so that improved performance of PIR-based techniques could be achieved. Numerical experiments demonstrate that the proposed techniques indeed deliver better efficiency under various criteria.

Lecture Notes in Computer Science, 2005

Communications in Computer and Information Science, 2014

The rise of Social Networking Services (SNSs) has not only transformed people as well as consumer... more The rise of Social Networking Services (SNSs) has not only transformed people as well as consumer behavior on the Internet, but also transformed the means by which various enterprises globally conduct their promotional and marketing campaigns. There are a variety of means by which enterprises have launched their marketing campaigns on Social Networking Services, and one of the most common techniques adopted is through extensive advertising campaigns on SNSs. This study seeks to examine consumer behaviors towards advertisements on Social Networking Services. Key factors affecting consumer behaviors include usage pattern, the credibility of a particular Social Networking Service as well as electronic word-of-mouth. This clearly illustrates that in today’s virtual electronic world, social media have progressed from being merely a place to meet people, to being a virtual sales floor. It is unexpected that consumer behaviors are influenced by the electronic word-of-mouth of friends rather than that of strangers.

Journal of Intelligent & Fuzzy Systems, 2014

Growing popularity of social networking not only brings the convenience of information sharing bu... more Growing popularity of social networking not only brings the convenience of information sharing but also concerns of privacy breaches. Information on social networks can be modeled as un-weighted or weighted graph data. To preserve privacy, k-anonymity on relational, set-valued, and graph data have been studied extensively in recent years. In this work, we consider the edge weight anonymity problem. In particular, to protect the weight privacy of the shortest path between two vertices on a weighted graph, we present a new concept called k-anonymous path privacy. A published social network graph with k-anonymous path privacy has at least k indistinguishable shortest paths between the source and destination vertices. Three greedy-based modification algorithms, based on modifying different types of edges, to achieve k-anonymous path privacy are proposed. Experimental results showing the feasibility and characteristics of the proposed approach are presented. The proposed techniques clearly provide different options to achieve the same level of privacy under different requirements.

Proceedings of the The 3rd Multidisciplinary International Social Networks Conference on SocialInformatics 2016, Data Science 2016, 2016

Opinion mining is a very hot and important issue of social media related researches, due to it is... more Opinion mining is a very hot and important issue of social media related researches, due to it is helpful for understanding the opinion of users in social media. In our previous research, we have already developed an approach to detect an important effect, which is called "Spiral of Silence (SoS)". The approach is developed based on opinion mining and sentimental analysis. In this paper, we will use the approach to test related issues of SoS in social medias and try to understand the difference between these social media platforms. Analysis results are also presented in the paper as well as discussions.

J. Univers. Comput. Sci., 2012

With the rapid growth of Internet and social networking websites, various services are provided i... more With the rapid growth of Internet and social networking websites, various services are provided in these platforms. For instance, Facebook focuses on social activities, Twitter and Plurk (which are called microblogs) are both focusing on the interaction of users through short messages. Millions of users enjoy services from these websites which are full of marketing possibilities. Understanding the users can assist companies to enhance the accuracy and efficiency of the target market. In this paper, a social recommendation system based on the data from microblogs is proposed. This social recommendation system is built according to the messages and social structure of target users. The similarity of the discovered features of users and products will then be calculated as the essence of the recommendation engine. A case study included in the paper presents how the recommendation system works based on real data from Plurk.

J. Web Eng., 2016

Privacy-preserving computation has recently attracted much attention in areas of transaction, soc... more Privacy-preserving computation has recently attracted much attention in areas of transaction, social networking, location-based, and mobile services. The inexpensive storage and efficient computation of cloud computing technology is expected to further escalate these services to a higher and wider level, without compromising the breaches of sensitive information. In this work, we study the shortest path distance computing in the cloud while preserving two types of privacy in the same time: k-neighborhood privacy and sensitive path privacy. We propose a new privacy model called (k, p)-shortest path neighborhood privacy, which is an extension of [19] and more flexible than 1-neighborhood-d-radius model. We also develop an efficient four-step shortest distance computation scheme to achieve (k, p)-shortest path neighborhood privacy on p outsourced servers in the cloud, which combines the construction of k-skip shortest path sub-graphs, sensitive vertex adjustment, vertex hierarchy labeling and bottom-up partitioning techniques. Numerical experiments show that the proposed approach is more efficient than prior model of constructing the 1-neighborhood privacy graph and also requires less querying time.

2017 International Conference on Behavioral, Economic, Socio-cultural Computing (BESC), 2017

In recent years, users are widely intend to express and share their opinions over the Internet. H... more In recent years, users are widely intend to express and share their opinions over the Internet. However, due to the characters of social media, it appears negative use of social media. Cyberbullying is one of the abuse behavior in the Internet as well as a very serious social problem. Under this background and motivation, it can help to prevent the happen of cyberbullying if we can develop relevant techniques to discover cyberbullying in social media. Thus, in this paper we propose an approach based on social networks analysis and data mining for cyberbullying detection. In the approach, there are three main techniques for cyberbullying discovery will be studied, including keyword matching technique, opinion mining and social network analysis. In addition to the approach, we will also discuss the experimental design for the evaluation of the performance.

2011 International Conference on Advances in Social Networks Analysis and Mining, 2011

2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, 2012

2013 IEEE International Conference on Systems, Man, and Cybernetics, 2013

ABSTRACT Preserving privacy in social networking environment has been studied extensively in rece... more ABSTRACT Preserving privacy in social networking environment has been studied extensively in recent years. Although more works have adopted un-weighted graphs to model network relationships, weighted graph modeling can provide deeper analysis of the degree of relationships. Previous works on weighted graph privacy have concentrated on preserving the shortest path characteristic between pairs of vertices. Two common types of privacy have been proposed. One type of privacy tried to add random noise edge weights to the graph but still maintain the same shortest path. The other privacy, k-shortest path privacy, minimally perturbed edge weights so that there exist k shortest paths. However, the k-shortest path privacy did not consider degree attacks on the nodes of anonymized shortest paths. For example, if the adversary possesses background knowledge of node degrees on the shortest path, the true shortest path can be identified. In this work, we present a new concept called (k1, k2)-shortest path privacy to prevent such privacy breach. A published network graph with (k1, k2)-shortest path privacy has at least k1 indistinguishable shortest paths between the source and destination vertices. In addition, for the non-overlapping vertices on the k1 shortest paths, there exist at least k2 vertices with same node degree and lie on more than one shortest path. Three heuristic algorithms are proposed and experimental results showing the feasibility and characteristics of the proposed approaches are presented.

Proceedings of International Conference on Information Integration and Web-based Applications & Services - IIWAS '13, 2013

ABSTRACT Efficient shortest path calculation has been studied extensively, in particular, in the ... more ABSTRACT Efficient shortest path calculation has been studied extensively, in particular, in the distributed environment. However, preserving privacy in the cloud environment has just attracted latest attention. To preserve fixed-pattern one-neighborhood privacy in the cloud, current approach requires the calculation of all-pairs shortest paths in advance, which is time consuming for large graphs. In addition, specific paths that are sensitive and require hiding the source and destination vertices are not well addressed. In this work, we propose a new flexible k-neighborhood privacy-protection and efficient shortest distance computation scheme for sensitive shortest paths in the cloud environment. Combining the construction of k-skip shortest path sub-graphs, sensitive vertex adjustment, vertex hierarchy labeling and bottom-up partitioning techniques, the proposed approach not only subsumes one-neighborhood privacy but also provides efficient partitioning and query processing for sensitive shortest paths. Numerical experiments demonstrating the characteristics of proposed approach are presented.

Springer Proceedings in Complexity, 2013

The explosive growth of the Internet has made information on the web large and complicated. If th... more The explosive growth of the Internet has made information on the web large and complicated. If the structure of a website is not optimized, users could easily get lost and could not find the most important information at the first time. The adaptive website can present the information that users needed by analyzing the users’ behavior. However, visitors may have different needs at different times. Most of recommended methods are not considerate of dynamic or time-dependent needs. This paper presents a recommender system based on reinforcement learning. We assume that five parameters are on recommendation, which include clicks of the page, time that spent on viewing the page, paths to find the page, hierarchy of the page, and the rank of the page. With the help of reinforcement learning to adjust the weight of five parameters, we aim to reduce the paths that user needed to find the object page.

Springer Proceedings in Complexity, 2013

Privacy preserving network publishing has been studied extensively in recent years. Although more... more Privacy preserving network publishing has been studied extensively in recent years. Although more works have adopted un-weighted graphs to model network relationships, weighted graph modeling can provide deeper analysis of the degree of relationships. Previous works on weighted graph privacy have concentrated on preserving the shortest path characteristic between pairs of vertices. Two common types of privacy have been proposed. One type of privacy tried to add random noise edge weights to the graph but still maintain the same shortest path. The other privacy, k-shortest path privacy, minimally perturbed edge weights so that there exist k shortest paths. However, the k-shortest path privacy did not consider degree attacks on the nodes of anonymized shortest paths. For example, if the adversary possesses background knowledge of node degrees on the shortest path, the true shortest path can be identified. We have previously presented a new concept called (k 1 , k 2 )-shortest path privacy to prevent such privacy breach [1]. A published network graph with (k 1 , k 2 )-shortest path privacy has at least k 1 indistinguishable shortest paths between the source and destination vertices. In addition, for the non-overlapping vertices on the k 1 shortest paths, there exist at least k 2 vertices with same node degree and lie on more than one shortest path. In this work, we further propose edge insertion and edge weight determination techniques to effectively achieve the proposed privacy. Numerical comparisons based on average clustering coefficient and average shortest path length show that the proposed TNF approach is simple and effective.

Springer Proceedings in Complexity, 2013

In recent years, with the growth of social networking websites, users are very active in these pl... more In recent years, with the growth of social networking websites, users are very active in these platforms and a large amount of data is aggregated. Among those social networking websites, Facebook is the most popular one that has most users. However, in Facebook, the existence of Hate Groups is a very critical issue with the problem of abusing. Therefore, many researchers are devoting themselves to detecting the potential hate groups, using the techniques of social networks analysis and web mining. In this paper, we will propose an approach based on the techniques of social networks analysis and web mining to detect the potential hate groups. The data from Facebook are being processed. In the research, hate groups for 3C are selected as the training data. The social network structures and keywords of these groups will be treated as the features which will be used for discovering the potential hate groups in Facebook.

Lecture Notes in Computer Science, 2011

2011 Second International Conference on Innovations in Bio-inspired Computing and Applications, 2011

Springer Proceedings in Complexity, 2013

International Journal of Data Warehousing and Mining, 2013

Location and local service is one of the hottest bunches of applications in recent years, due to ... more Location and local service is one of the hottest bunches of applications in recent years, due to the proliferation of Global Position System (GPS) and mobile web search technology. Spatial queries retrieving neighboring Point-Of-Interests (POI) require actual user locations for services. However, exposing the physical location of querier to service system may pose privacy threat to users, if malicious adversary has access to the system. To hinder the service system from obtaining the “true” location of querier, current obfuscation-based approach requires a trusted third party anonymizer. As for the data-encryption-based and cPIR-based approaches, they incur costly computation overheads. Although the secure hardware-aided PIR-based technique has been shown to be superior to formers, it did not consider the characteristics of data distribution of searching domain. To deal with the problem of non-uniform data distribution and efficient retrieval, we propose four schemes: MSQL, NSQL, MN...

2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2012

ABSTRACT Due to the proliferation of Global Position System (GPS) and smart phone technology, Loc... more ABSTRACT Due to the proliferation of Global Position System (GPS) and smart phone technology, Location-Based Service (LBS) has attained tremendous growth in recent years. Spatial queries retrieving nearest Point-Of-Interests (POI) require actual user locations for services. However, sharing such sensitive personal location information with potentially malicious servers may cause concerns about user privacy. The current obfuscation-based approach addressing this problem cannot provide binding privacy guarantees as a trusted third-party anonymizer is required. On the other hand, the data-encryption-based and cPIR-based approaches incur costly computation overheads. Recently, the secure hardware-aided PIR-based technique has been shown to be superior to formers, but it did not consider the characteristics of data distribution of searching domain. In this work, we propose two schemes: MSQL, NSQL, based on flexible multi-layer grids and non-empty lookup table for efficient storage and retrieval on non-uniform distribution of POI data, so that improved performance of PIR-based techniques could be achieved. Numerical experiments demonstrate that the proposed techniques indeed deliver better efficiency under various criteria.

Lecture Notes in Computer Science, 2005