The Experts below are selected from a list of 72 Experts worldwide ranked by ideXlab platform
Kristina Lisa Klinkner - One of the best experts on this subject based on the ideXlab platform.
-
beyond the Session Timeout automatic hierarchical segmentation of search topics in query logs
Conference on Information and Knowledge Management, 2008Co-Authors: Rosie Jones, Kristina Lisa KlinknerAbstract:Most analysis of web search relevance and performance takes a single query as the unit of search engine interaction. When studies attempt to group queries together by task or Session, a Timeout is typically used to identify the boundary. However, users query search engines in order to accomplish tasks at a variety of granularities, issuing multiple queries as they attempt to accomplish tasks. In this work we study real Sessions manually labeled into hierarchical tasks, and show that Timeouts, whatever their length, are of limited utility in identifying task boundaries, achieving a maximum precision of only 70%. We report on properties of this search task hierarchy, as seen in a random sample of user interactions from a major web search engine's log, annotated by human editors, learning that 17% of tasks are interleaved, and 20% are hierarchically organized. No previous work has analyzed or addressed automatic identification of interleaved and hierarchically organized search tasks. We propose and evaluate a method for the automated segmentation of users' query streams into hierarchical units. Our classifiers can improve on Timeout segmentation, as well as other previously published approaches, bringing the accuracy up to 92% for identifying fine-grained task boundaries, and 89-97% for identifying pairs of queries from the same task when tasks are interleaved hierarchically. This is the first work to identify, measure and automatically segment sequences of user queries into their hierarchical structure. The ability to perform this kind of segmentation paves the way for evaluating search engines in terms of user task completion.
-
CIKM - Beyond the Session Timeout: automatic hierarchical segmentation of search topics in query logs
Proceeding of the 17th ACM conference on Information and knowledge mining - CIKM '08, 2008Co-Authors: Rosie Jones, Kristina Lisa KlinknerAbstract:Most analysis of web search relevance and performance takes a single query as the unit of search engine interaction. When studies attempt to group queries together by task or Session, a Timeout is typically used to identify the boundary. However, users query search engines in order to accomplish tasks at a variety of granularities, issuing multiple queries as they attempt to accomplish tasks. In this work we study real Sessions manually labeled into hierarchical tasks, and show that Timeouts, whatever their length, are of limited utility in identifying task boundaries, achieving a maximum precision of only 70%. We report on properties of this search task hierarchy, as seen in a random sample of user interactions from a major web search engine's log, annotated by human editors, learning that 17% of tasks are interleaved, and 20% are hierarchically organized. No previous work has analyzed or addressed automatic identification of interleaved and hierarchically organized search tasks. We propose and evaluate a method for the automated segmentation of users' query streams into hierarchical units. Our classifiers can improve on Timeout segmentation, as well as other previously published approaches, bringing the accuracy up to 92% for identifying fine-grained task boundaries, and 89-97% for identifying pairs of queries from the same task when tasks are interleaved hierarchically. This is the first work to identify, measure and automatically segment sequences of user queries into their hierarchical structure. The ability to perform this kind of segmentation paves the way for evaluating search engines in terms of user task completion.
Rosie Jones - One of the best experts on this subject based on the ideXlab platform.
-
beyond the Session Timeout automatic hierarchical segmentation of search topics in query logs
Conference on Information and Knowledge Management, 2008Co-Authors: Rosie Jones, Kristina Lisa KlinknerAbstract:Most analysis of web search relevance and performance takes a single query as the unit of search engine interaction. When studies attempt to group queries together by task or Session, a Timeout is typically used to identify the boundary. However, users query search engines in order to accomplish tasks at a variety of granularities, issuing multiple queries as they attempt to accomplish tasks. In this work we study real Sessions manually labeled into hierarchical tasks, and show that Timeouts, whatever their length, are of limited utility in identifying task boundaries, achieving a maximum precision of only 70%. We report on properties of this search task hierarchy, as seen in a random sample of user interactions from a major web search engine's log, annotated by human editors, learning that 17% of tasks are interleaved, and 20% are hierarchically organized. No previous work has analyzed or addressed automatic identification of interleaved and hierarchically organized search tasks. We propose and evaluate a method for the automated segmentation of users' query streams into hierarchical units. Our classifiers can improve on Timeout segmentation, as well as other previously published approaches, bringing the accuracy up to 92% for identifying fine-grained task boundaries, and 89-97% for identifying pairs of queries from the same task when tasks are interleaved hierarchically. This is the first work to identify, measure and automatically segment sequences of user queries into their hierarchical structure. The ability to perform this kind of segmentation paves the way for evaluating search engines in terms of user task completion.
-
CIKM - Beyond the Session Timeout: automatic hierarchical segmentation of search topics in query logs
Proceeding of the 17th ACM conference on Information and knowledge mining - CIKM '08, 2008Co-Authors: Rosie Jones, Kristina Lisa KlinknerAbstract:Most analysis of web search relevance and performance takes a single query as the unit of search engine interaction. When studies attempt to group queries together by task or Session, a Timeout is typically used to identify the boundary. However, users query search engines in order to accomplish tasks at a variety of granularities, issuing multiple queries as they attempt to accomplish tasks. In this work we study real Sessions manually labeled into hierarchical tasks, and show that Timeouts, whatever their length, are of limited utility in identifying task boundaries, achieving a maximum precision of only 70%. We report on properties of this search task hierarchy, as seen in a random sample of user interactions from a major web search engine's log, annotated by human editors, learning that 17% of tasks are interleaved, and 20% are hierarchically organized. No previous work has analyzed or addressed automatic identification of interleaved and hierarchically organized search tasks. We propose and evaluate a method for the automated segmentation of users' query streams into hierarchical units. Our classifiers can improve on Timeout segmentation, as well as other previously published approaches, bringing the accuracy up to 92% for identifying fine-grained task boundaries, and 89-97% for identifying pairs of queries from the same task when tasks are interleaved hierarchically. This is the first work to identify, measure and automatically segment sequences of user queries into their hierarchical structure. The ability to perform this kind of segmentation paves the way for evaluating search engines in terms of user task completion.
James Miller - One of the best experts on this subject based on the ideXlab platform.
-
empirical observations on the Session Timeout threshold
Information Processing and Management, 2009Co-Authors: Toan Huynh, James MillerAbstract:The World Wide Web is a popular ''tool'' for companies. It can be used as a method of communication between companies and their customers; it also allows organizations to setup virtual storefronts that can be accessed by customers from all over the world. The ability to understand customers' behavior is extremely important as companies strive to increase the usability and profitability of their web service. The concept of a Session is a popular unit of measurement used to analyze recorded information. However, this concept is currently rather abstract and lacks definition. How we measure a Session is a fundamental question for web services utilizing this concept. Currently, this question has no real answer. This paper presents a Session Timeout threshold model based on empirical observations as an initial answer to this question. The model seeks to provide accurate Session data with respect to individual web services.
S. Zeidan - One of the best experts on this subject based on the ideXlab platform.
-
Enhanced Session Table Architecture for Stateful Firewalls
2018 IEEE International Conference on Communications (ICC), 2018Co-Authors: Z. Trabelsi, S. ZeidanAbstract:Stateful firewall keeps track of the state of network connections. The performance of stateful firewall determines by both the performance of its Session table and the mechanism used for packet filtering. This paper presents a stateful Session table architecture then integrates it with Splay tree firewall. Splay tree firewall organizes policy rules in a designated prefix length splay tree data structure, and a collection of hash tables grouped by prefix length. Packet filtering time using Splay tree firewall is essentially reduced through multilevel filtering paths, where unwanted packets are rejected as early as possible. The proposed Session table architecture reduces memory space consumption and Session operations time, as it uses one hash slot per connection. Keeping all connection related information in one Session entry produces additional processing time, particularly for Session Timeout attribute processing. Our proposed Session architecture separates Session state and Timeout attributes information into different data structures to enhance the overall system performance.
-
ICC - Enhanced Session Table Architecture for Stateful Firewalls
2018 IEEE International Conference on Communications (ICC), 2018Co-Authors: Z. Trabelsi, S. ZeidanAbstract:Stateful firewall keeps track of the state of network connections. The performance of stateful firewall determines by both the performance of its Session table and the mechanism used for packet filtering. This paper presents a stateful Session table architecture then integrates it with Splay tree firewall. Splay tree firewall organizes policy rules in a designated prefix length splay tree data structure, and a collection of hash tables grouped by prefix length. Packet filtering time using Splay tree firewall is essentially reduced through multilevel filtering paths, where unwanted packets are rejected as early as possible. The proposed Session table architecture reduces memory space consumption and Session operations time, as it uses one hash slot per connection. Keeping all connection related information in one Session entry produces additional processing time, particularly for Session Timeout attribute processing. Our proposed Session architecture separates Session state and Timeout attributes information into different data structures to enhance the overall system performance.
Piotr Kuna - One of the best experts on this subject based on the ideXlab platform.
-
Student’s Behavior in Virtual Environment
Interactive Collaborative Learning, 2017Co-Authors: Piotr Kuna, Martin VozarAbstract:The analysis of students behaviour in web learning environment within distance learning is one of the most significant areas for learning optimization. The aim of this article is to analyse student’s behaviour and the use of e-learning course in subject Discrete Mathematics. Data and results of this analysis are important for further adjustment and improvement of the e-course. Results of the course traffic analysis were estimated using association rules Discrete mathematics is compulsory for both bachelor and master study program Applied Informatics in full-time and distance form of study as well as bachelor and master study program Teaching of academic subjects in full-time and distance form of study. This electronic course is designed to use linear and branched teaching programs. In compiling the course we tried to take into consideration target audience - students of Computer Science. The course is designed to not require any special knowledge in IT field. Discrete Mathematics Course 1 consists of 10 thematic units (areas) replicating the length of the semester in weeks. Authors describe detail analysis of student’s behaviour which is made of data taken from LMS MOODLE database. We used specific types of data, which are indicating user traffic on every single page of the course. We used a log file that contains records of e-learning course with 107 students. To identify Sessions, we used the STT (Session Timeout Threshold). Purpose of Session identification is to divide access of all users into separate Sessions (relations). Session side-effect may exclude users who are behind a NAT or proxy device. So we can identify users who are sharing a single computer, for example in a library. Students who used the e-course of Discrete Mathematics 1 were more successful in the final examination. The fact that the course is effective does not mean that all activities have been fully utilized. Based on the results of our analysis, we can optimize and improve the e-course and bring it closer to the student’s needs. After implementation of necessary changes we can evaluate impact of these changes in the efficacy of the course.
-
Student’s behavior in virtual environment
19th International Conference on Interactive Collaborative Learning ICL 2016, 2017Co-Authors: Piotr Kuna, Martin VozarAbstract:The analysis of students behaviour in web learning environment within distance learning is one of the most significant areas for learning optimization. The aim of this article is to analyse student’s behaviour and the use of e-learning course in subject Discrete Mathematics. Data and results of this analysis are important for further adjustment and improvement of the e-course. Results of the course traffic analysis were estimated using association rules Discrete mathematics is compulsory for both bachelor and master study program Applied Informatics in full-time and distance form of study as well as bachelor and master study program Teaching of academic subjects in full-time and distance form of study. This electronic course is designed to use linear and branched teaching programs. In compiling the course we tried to take into consideration target audience-students of Computer Science. The course is designed to not require any special knowledge in IT field. Discrete Mathematics Course 1 consists of 10 thematic units (areas) replicating the length of the semester in weeks. Authors describe detail analysis of student’s behaviour which is made of data taken from LMS MOODLE database. We used specific types of data, which are indicating user traffic on every single page of the course. We used a log file that contains records of e-learning course with 107 students. To identify Sessions, we used the STT (Session Timeout Threshold). Purpose of Session identification is to divide access of all users into separate Sessions (relations). Session side-effect may exclude users who are behind a NAT or proxy device. So we can identify users who are sharing a single computer, for example in a library. Students who used the e-course of Discrete Mathematics 1 were more successful in the final examination. The fact that the course is effective does not mean that all activities have been fully utilized. Based on the results of our analysis, we can optimize and improve the e-course and bring it closer to the student’s needs. After implementation of necessary changes we can evaluate impact of these changes in the efficacy of the course. © Springer International Publishing AG 2017.
-
Analysis of students behaviour in virtual environment
2014 IEEE 12th IEEE International Conference on Emerging eLearning Technologies and Applications (ICETA), 2014Co-Authors: J. Reichel, Piotr KunaAbstract:The analysis of students behaviour in web learning environment within distance learning is one of the most significant areas for learning optimization. The aim of this article is to analyse students behaviour and the use of e-learning course in subject Discrete Mathematics. Data and results of this analysis are important for further adjustment and improvement of the e-course. Results of the course traffic analysis were estimated using association rules Discrete mathematics is compulsory for both bachelor and master study program Applied Informatics in full-time and distance form of study as well as bachelor and master study program Teaching of academic subjects in full-time and distance form of study. This electronic course is designed to use linear and branched teaching programs. In compiling the course we tried to take into consideration target audience - students of Computer Science. The course is designed to not require any special knowledge in IT field. Discrete Mathematics Course 1 consists of 10 thematic units (areas) replicating the length of the semester in weeks. Authors describe detail analysis of students behaviour which is made of data taken from LMS MOODLE database. We used specific types of data, which are indicating user traffic on every single page of the course. We used a log file that contains records of e-learning course with 107 students. To identify Sessions, we used the STT (Session Timeout Threshold). Purpose of Session identification is to divide access of all users into separate Sessions (relations). Session side-effect may exclude users who are behind a NAT or proxy device. So we can identify users who are sharing a single computer, for example in a library. Students who used the e-course of Discrete Mathematics 1 were more successful in the final examination. The fact that the course is effective does not mean that all activities have been fully utilized. Based on the results of our analysis, we can optimize and improve the e-course and bring it closer to the student's needs. After implementation of necessary changes we can evaluate impact of these changes in the efficacy of the course.