Improved Probability Estimator for Human Session Interaction Patterns Using Graph Based Algorithm
 |
International Journal of Computer & Organization Trends (IJCOT) | 
|
| © 2015 by IJCOT Journal | ||
| Volume - 5 Issue - 1 |
||
| Year of Publication : 2015 | ||
| Authors : P.Naga Revathi Manjusha , S.Sailaja | ||
| DOI : 10.14445/22492593/IJCOT-V16P302 |
Citation
P.Naga Revathi Manjusha , S.Sailaja "Improved Probability Estimator for Human Session Interaction Patterns Using Graph Based Algorithm", International Journal of Computer & organization Trends (IJCOT), V5(1):6-13 Jan 2015, ISSN:2249-2593, www.ijcotjournal.org. Published by Seventh Sense Research Group.
Abstract
Mining human decision patterns in the meetings or any business interactions are useful to identify the person’s opinion within the session. Activities in the session represent the origins of an individual and mining methods assist to analyze how person delivers their opinion at different paths. In this proposed work, meeting interactions are classified as comment, propose, request-information, acknowledgement, ask, positive and negative opinion. Traditional human interaction techniques are used to detect and analyze patterns to find various types of new knowledge on interactions. Traditional methods fail to extract sub frequent patterns in the interaction flow. Human interaction flow is represented as graph along with their opinions. Graph based pattern mining algorithm was planned to extract relevant patterns from the meeting interaction dataset. Proposed work has extended to extract interaction patterns using DAG (Directed Acyclic Graph) based mining algorithm. Graph-based Substructure mining algorithm which discovers the frequent substructure paths from the candidate patterns of DAG algorithm. Substructures help to predict the probability of associate patterns within the session. Proposed algorithm efficiently uses different support and confident measures to extract user interaction patterns. Experimental study shows that the proposed model extract high relevant interaction patterns with less time and high accuracy.
References
[1] Mining Human Decision Patterns Using Weighted Substructure DAG algorithm, K.Aparna and k .Venkataraju, International Journal of Applied Engineering Research (IJAER).
[2] HIDDEN INTERACTION PATTERN DISCOVERY OF HUMAN INTERACTION IN MEETINGS,.
[3] DETECTING INTEREST LEVEL PATTERNS OF HUMAN INTERACTION USING TREE BASED MINING, Sahaya Sachithananthi Yesuraj , C. Balasubramanian, International Journal of Emerging Technology and Advanced Engineering, Volume 3, Special Issue 1, January 2013
[4] An Efficient Interaction Pattern Discovery For Human Meetings, A.Nandha Kumar , N.Baskar, International Journal of Computer Trends and Technology (IJCTT) - volume4 Issue5–May 2013. [5] Modeling Human-Agent Interaction with Active Ontologies, Didier Guzzoni and Charles Baur, Adam Cheyer.
[6] Discovering Patterns in Interactions between Humans and Animals by Using Tree Based Mining, Palivela Hemant, VijayKumar S, Sharadha K A, International Journal of Engineering Research & Technology.
[7] OPINION MINING AND ANALYSIS: A SURVEY, Arti Buche, International Journal on Natural Language Computing (IJNLC) Vol. 2, No.3, June 2013.
[8] Classification of Opinion Mining Techniques, Nidhi MishraInternational Journal of Computer Applications (0975 – 8887) Volume 56– No.13, October 2012.
[9] METHODOLOGICAL STUDY OF OPINION MINING AND SENTIMENT ANALYSIS TECHNIQUES, Pravesh Kumar Singh, International Journal on Soft Computing (IJSC) Vol. 5, No. 1, February 2014
Keywords
Human Meeting, Decision Patterns, Support,Substructure.