2017 International Conference on Information and Communications (ICIC)
Job recommender is a system that automatically returns a ranked list of suitable, prospective job... more Job recommender is a system that automatically returns a ranked list of suitable, prospective jobs for employees. It plays a significant role in connecting employees and employers. In order to choose a suitable algorithm to build the system, a comparison study of popular recommendation methods is conducted and reported in this paper. The experimental data crawled from vietnamworks.com, itviec.com and careerlink.vn. A subset includes 7623 jobs extracted for running experiment. There are totally 59 users who have joint in rating jobs as well as giving feedback to measure performance of different methods. The experimental results demonstrated that content based approach is outperform than other tradictional ones.
2016 3rd National Foundation for Science and Technology Development Conference on Information and Computer Science (NICS), 2016
Job recommender systems are designed to suggest a ranked list of jobs that could be associated wi... more Job recommender systems are designed to suggest a ranked list of jobs that could be associated with employee's interest. Most of existing systems use only one approach to make recommendation for all employees, while a specific method normally is good enough for a group of employees. Therefore, this study proposes an adaptive solution to make job recommendation for different groups of user. The proposed methods are based on employee clustering. Firstly, we group employees into different clusters. Then, we select a suitable method for each user cluster based on empirical evaluation. The proposed methods include CB-Plus, CF-jFilter and HyR-jFilter have applied for different three clusters. Empirical results show that our proposed methods is outperformed than traditional methods.
To study about the state of the art for a research project, researchers must conduct a literature... more To study about the state of the art for a research project, researchers must conduct a literature survey by searching for, collecting , and reading related scientific publications. By using popular search systems, online digital libraries, and Web of Science (WoS) sources such as IEEE Explorer, ACM, SpringerLink, and Google Scholar, researchers could easily search for necessary publications related to their research interest. However, the rapidly increasing number of research papers published each year is a major challenge for researchers in searching for relevant information. Therefore, the aim of this study is to develop new methods for recommending scientific publications for researchers automatically. The proposed ones are based on exploiting explicit and implicit relations in the academic field. Experiments are conducted on a dataset crawled from Microsoft Academic Search [1]. The experimental results show that our proposed methods are very potential in recommending publications that are meet with research interest of researchers.
International Conference on Education and Management Technology, 2010
In this paper we propose a method to extract automatically metadata (title, authors, affiliation,... more In this paper we propose a method to extract automatically metadata (title, authors, affiliation, email, references, etc) from science papers by combining the layout information of papers with rules which are defined by using JAPE Grammar rules of GATE. After metadata extracted automatically from digital documents, user can interact and correct them before they are exported to XML files. Developing a tool to extract metadata from digital documents is a very necessary and useful task for building collections, organizing and searching documents in digital libraries. The extraction method is tested on computer science paper collections selected from international journals, proceedings downloaded from digital libraries such as ACM, IEEE, Springer and CiteSeer.
ABSTRACT To learn about the state of the art for a research project, researchers must conduct a l... more ABSTRACT To learn about the state of the art for a research project, researchers must conduct a literature survey by searching for, collecting, and reading related scientific articles. Popular search systems, online digital libraries, and Web of Science (WoS) sources such as IEEE Explorer, ACM, SpringerLink, and Google Scholar typically return results or articles that are similar to keywords in the user's query. Some digital libraries also include content-based recommenders that suggest papers similar to one the user likes based on the contents of paper, i.e., the keywords it contains. In this work, we present a recommender module that suggests papers to users based on the seed paper's Citation Network. This work takes into account the combination of the co-citation and co-reference factors to improve algorithm's effectiveness. We applied and improved the the CCIDF (Common Citation Inverse Document Frequency) algorithm used by the CiteSeer digital library. This improved algorithm, called CCIDF+, was evaluated using data collected from Microsoft Academic Search (MAS). Experimental results show that CCIDF+ outperforms CCIDF.
2017 International Conference on Information and Communications (ICIC)
Job recommender is a system that automatically returns a ranked list of suitable, prospective job... more Job recommender is a system that automatically returns a ranked list of suitable, prospective jobs for employees. It plays a significant role in connecting employees and employers. In order to choose a suitable algorithm to build the system, a comparison study of popular recommendation methods is conducted and reported in this paper. The experimental data crawled from vietnamworks.com, itviec.com and careerlink.vn. A subset includes 7623 jobs extracted for running experiment. There are totally 59 users who have joint in rating jobs as well as giving feedback to measure performance of different methods. The experimental results demonstrated that content based approach is outperform than other tradictional ones.
2016 3rd National Foundation for Science and Technology Development Conference on Information and Computer Science (NICS), 2016
Job recommender systems are designed to suggest a ranked list of jobs that could be associated wi... more Job recommender systems are designed to suggest a ranked list of jobs that could be associated with employee's interest. Most of existing systems use only one approach to make recommendation for all employees, while a specific method normally is good enough for a group of employees. Therefore, this study proposes an adaptive solution to make job recommendation for different groups of user. The proposed methods are based on employee clustering. Firstly, we group employees into different clusters. Then, we select a suitable method for each user cluster based on empirical evaluation. The proposed methods include CB-Plus, CF-jFilter and HyR-jFilter have applied for different three clusters. Empirical results show that our proposed methods is outperformed than traditional methods.
To study about the state of the art for a research project, researchers must conduct a literature... more To study about the state of the art for a research project, researchers must conduct a literature survey by searching for, collecting , and reading related scientific publications. By using popular search systems, online digital libraries, and Web of Science (WoS) sources such as IEEE Explorer, ACM, SpringerLink, and Google Scholar, researchers could easily search for necessary publications related to their research interest. However, the rapidly increasing number of research papers published each year is a major challenge for researchers in searching for relevant information. Therefore, the aim of this study is to develop new methods for recommending scientific publications for researchers automatically. The proposed ones are based on exploiting explicit and implicit relations in the academic field. Experiments are conducted on a dataset crawled from Microsoft Academic Search [1]. The experimental results show that our proposed methods are very potential in recommending publications that are meet with research interest of researchers.
International Conference on Education and Management Technology, 2010
In this paper we propose a method to extract automatically metadata (title, authors, affiliation,... more In this paper we propose a method to extract automatically metadata (title, authors, affiliation, email, references, etc) from science papers by combining the layout information of papers with rules which are defined by using JAPE Grammar rules of GATE. After metadata extracted automatically from digital documents, user can interact and correct them before they are exported to XML files. Developing a tool to extract metadata from digital documents is a very necessary and useful task for building collections, organizing and searching documents in digital libraries. The extraction method is tested on computer science paper collections selected from international journals, proceedings downloaded from digital libraries such as ACM, IEEE, Springer and CiteSeer.
ABSTRACT To learn about the state of the art for a research project, researchers must conduct a l... more ABSTRACT To learn about the state of the art for a research project, researchers must conduct a literature survey by searching for, collecting, and reading related scientific articles. Popular search systems, online digital libraries, and Web of Science (WoS) sources such as IEEE Explorer, ACM, SpringerLink, and Google Scholar typically return results or articles that are similar to keywords in the user's query. Some digital libraries also include content-based recommenders that suggest papers similar to one the user likes based on the contents of paper, i.e., the keywords it contains. In this work, we present a recommender module that suggests papers to users based on the seed paper's Citation Network. This work takes into account the combination of the co-citation and co-reference factors to improve algorithm's effectiveness. We applied and improved the the CCIDF (Common Citation Inverse Document Frequency) algorithm used by the CiteSeer digital library. This improved algorithm, called CCIDF+, was evaluated using data collected from Microsoft Academic Search (MAS). Experimental results show that CCIDF+ outperforms CCIDF.
Uploads
Papers by Tin Huynh