Worasit Choochaiwattana

A Framework for Tag-Based Research Paper Recommender System: An IR Approach

The Internet and the World Wide Web provide a way to store and share information, especially in academic fields. Community-based research paper sharing systems, such as CiteULike, have become popular among researchers. This paper proposes a framework for a tag-based research paper recommender system. The proposed approach exploits the use of sets of tags for recommending research papers to each user. The preliminary evaluation shows that user self-defined tags could be used as a profile for each individual user. This recommender system demonstrated an encouraging preliminary result with the overall accuracy percentage up to 91.66%.

Applying Social Annotations to Retrieve and Re-rank Web Resources

Web-base tagging systems, which include social bookmarking systems such as del.icio.us, have become increasingly popular. These systems allow participants to annotate or tag web resources. This paper examined the use of social annotations to improve the quality of web search. It involved two components. First, social annotations were used to index resources. Two annotation-based indexing methods were proposed. Second, social annotations were used to improve search result ranking. Four annotation-based ranking methods were proposed. The result showed that using only annotation as an index of resources may not be appropriate. Since social annotations could be viewed as a high level concept of the content, combining them to the content of resource could add some more important concepts to the resources. The result also suggested that both static feature and similarity feature should be considered when using social annotations to re-rank search result.

Usage of tagging for research paper recommendation

Tagging has become a common service on Web2.0 application. This kind of service allows users to share and annotate interesting web resources. CiteULike is an example of Web2.0 application that allows its users to share research papers based on their interest. It also allows the users to create annotations or tags attached to the research papers. This paper examined the use of tagging for research paper recommendation. A research paper recommendation mechanism based on tagging was proposed. This mechanism recommends a research paper according a set of tags they have created. The result suggested that tags created by each user could be used as a user individual profile. The profile then compared with research paper index to compute a similarity score. The result of experiment showed that the accuracy of the proposed research paper recommendation is 79% with f-measure value at 82%.

A comparison of search engine using “tag title and abstract” with CiteULike — An initial evaluation

At present, the performance and capabilities of web search engine are vital. Most researchers use search engines for research papers related to their topics of interest. This paper demonstrates the initial comparison search results between a search engine using the indexing method of “tag title and abstract” and the native CiteUlike engine. The retrieval performance of these two search engines are evaluated using mean values of Normalized Discount Cumulative Gain (NDCG). The results illustrate that the search engine with indexer using “tag, title, and abstract” provides better search results as compared to CiteUlike, particularly for those documents in the first two rank which would be considered as the most relevant documents. This primary evaluation in the experiments implies that the chosen heuristic indexer may improve the efficiency of web resource searching on social bookmarking websites.

Improving research paper searching with social tagging — A preliminary investigation

The WWW provides an efficient way to store and share information. Search engines and social bookmarking systems are important tools for web resource discovery. This study investigated three different indexing approaches applied to CiteULike — a social bookmarking system for tagging academic research papers. The indexing approaches here are known as: Tag only; Title with Abstract; and Tag, Title with Abstract. These three indexing approaches were evaluated using mean values of Normalized Discount Cumulative Gain (NDCG). The preliminary results illustrated that indexing using “Tag, Title, with Abstract” performed the best. The initial evaluation on our implementation implied that these designs might improve the accuracy and efficiency of web resource searching on social bookmarking system, not only in academics but also in other domains.

A comparison of driving behaviour prediction algorithm using multi-sensory data on a smartphone

The causes of accidents on highway in any countries come from vehicle condition, human error, and highway physical conditions. From the accident statistic on the highway in Thailand, the major cause of the accidents is from aggressive driving behaviour. One way to decrease highway traffic accidents is to provide some information, such as alerts and warnings to the car drivers. Currently, people all around the world use smartphones on a daily basis. Many useful applications can be installed on the smart phones. Thus, this paper presents drivers behaviour detection algorithm using multi-sensory data on a smartphone to detect driving events and provide real-time feedback to drivers while driving. From variation in hardware of device available, the algorithm allows user to customize the algorithm according to the device configuration. Pattern matching of different sensory data was applied to find driving event. The algorithm demonstrates 71 - 80% accuracy in correct prediction of driving events.

CiteRank: combination similarity and static ranking with research paper searching

Search engines and social bookmarking systems are important tools for web resource discovery. The performance and capabilities of web search engines are vital. This paper proposes CiteRank, a combination of a similarity ranking with a static ranking. Similarity ranking measures the match between a query and a research paper index; while a static ranking, or a query independent ranking, measures the quality of a research paper. For this particular study, a group of factors containing: number of groups contained the posted paper, year of publication, research paper posted time, and priority of a research paper was used to determine a static ranking score. The NDCG was used as an evaluation metric. CiteRank was compared with SimRank and StaticRank. The results of the experiment showed that CiteRank produces a better ranking than the other methods. This implies that CiteRank can improve the effectiveness of research paper searching on social bookmarking websites.

An Academic Search Engine for Personalized Rankings

Rapidly increasing information on the Internet and the World Wide Web can lead to information overload. Search engines become important tools to help WWW users to discover information. Exponential increases in published research papers, academic search engines become indispensable tools to search for papers in their expertise and related fields. In order to improve the quality of search, an academic search engines’ capability should be enhanced. This paper proposes a search engine for personalized rankings. In order to evaluate the performance of personalized rankings, thirty-five graduate students from the Department of Web Engineering and Mobile Application Development at Dhurakij Pundit University are participants in the research experiment. Participants are asked to use a prototype of an academic search engine to find and bookmark any research papers according to their interests, which would guarantee that each participants’ list of interesting research papers could be recorded. Normalized Discounted Cumulative Gain (NDCG) is used as a metric to determine the performance of the personalized rankings. The experiments suggest that the personalized rankings outperform the original search rankings. Hence, the proposed academic search engine with personalized ranking benefits research paper discovery.

A Hybrid Knowledge Discovery System Based on Items and Tags

Exponentially increasing knowledge in a management system is the main cause of the overload problem. Development of a recommender service embedded in the management system is challenging. This paper proposes a hybrid approach by combining an item-based recommendation technique (collaborative filtering technique) with a tagbased recommendation technique (content based filtering technique). In order to evaluate the performance of the proposed hybrid approach, a group of knowledge management system users are invited as participants in the research. Participants are asked to use the prototype of a management system embedded within the knowledge recommender service for four months, which guarantees that each interaction by participants with knowledge items are recorded. A confusion matrix is used to compute accuracy of the proposed hybrid approach. The results of the experiments reveal that the hybrid approach outperforms both item-based and tag-based approaches. The hybrid approach seems to be a promising technique for a recommender service in the knowledge management system.

A conceptual framework for digital annotation system on WWW

The Internet and World Wide Web provide new ways to create and store information. From the literature, there are several reasons why people annotate documents. Some people use annotation as a reminder of an interesting or important part in a document. Annotation can be used to support collaborative work and discussion. It can also be viewed as additional information to the whole document or selected parts for some purposes such as classification. Annotation can be created in different forms e.g. highlight, note and etc. People use different forms of annotation for different functions. This paper proposed a conceptual framework for a development of digital annotation system on WWW. The framework depicts the structural components for digital annotation system. Last but not lease we used the proposed framework to develop a digital annotation system on WWW. This system allows users to create annotations on any web pages. Users can add notes and tag and create highlight on web pages.