Presented by Archana Kumari ( ) | Supervised By Mr Vikram Singh

Slides:



Advertisements
Similar presentations
Effective Keyword Based Selection of Relational Databases Bei Yu, Guoliang Li, Karen Sollins, Anthony K.H Tung.
Advertisements

Project Proposal.
Mapping Studies – Why and How Andy Burn. Resources The idea of employing evidence-based practices in software engineering was proposed in (Kitchenham.
A review on “Answering Relationship Queries on the Web” Bhushan Pendharkar ASU ID
GENERATING AUTOMATIC SEMANTIC ANNOTATIONS FOR RESEARCH DATASETS AYUSH SINGHAL AND JAIDEEP SRIVASTAVA CS DEPT., UNIVERSITY OF MINNESOTA, MN, USA.
Dialogue – Driven Intranet Search Suma Adindla School of Computer Science & Electronic Engineering 8th LANGUAGE & COMPUTATION DAY 2009.
Search Engines and Information Retrieval
Information Retrieval February 24, 2004
Evaluating usability through claims analysis Suzette Keith Ann Blandford, Bob Fields, Richard Butterworth, Yin Leng Theng.
WebMiningResearch ASurvey Web Mining Research: A Survey By Raymond Kosala & Hendrik Blockeel, Katholieke Universitat Leuven, July 2000 Presented 4/18/2002.
An Overview of Relevance Feedback, by Priyesh Sudra 1 An Overview of Relevance Feedback PRIYESH SUDRA.
What is adaptive web technology?  There is an increasingly large demand for software systems which are able to operate effectively in dynamic environments.
Creating and Visualizing Document Classification J. Gelernter, D. Cao, R. Lu, E. Fink, J. Carbonell.
Personalization of the Digital Library Experience: Progress and Prospects Nicholas J. Belkin Rutgers University, USA
Search Engines and Information Retrieval Chapter 1.
Information in the Digital Environment Information Seeking Models Dr. Dania Bilal IS 530 Spring 2006.
Probabilistic Query Expansion Using Query Logs Hang Cui Tianjin University, China Ji-Rong Wen Microsoft Research Asia, China Jian-Yun Nie University of.
CSM06 Information Retrieval Lecture 6: Visualising the Results Set Dr Andrew Salway
Contextual Ranking of Keywords Using Click Data Utku Irmak, Vadim von Brzeski, Reiner Kraft Yahoo! Inc ICDE 09’ Datamining session Summarized.
Lecture 2 Jan 15, 2008 Social Search. What is Social Search? Social Information Access –a stream of research that explores methods for organizing users’
Personalized Course Navigation Based on Grey Relational Analysis Han-Ming Lee, Chi-Chun Huang, Tzu- Ting Kao (Dept. of Computer Science and Information.
Information in the Digital Environment Information Seeking Models Dr. Dania Bilal IS 530 Spring 2005.
 A Case For Interaction: A Study of Interactive Information Retrieval Behavior and Effectiveness By Jürgen Koenemann and Nicholas J. Belkin (1996) John.
VisDB: Database Exploration Using Multidimensional Visualization Maithili Narasimha 4/24/2001.
Information Retrieval in Context of Digital Libraries - or DL in Context of IR Peter Ingwersen Royal School of LIS Denmark –
Automatic Video Tagging using Content Redundancy Stefan Siersdorfer 1, Jose San Pedro 2, Mark Sanderson 2 1 L3S Research Center, Germany 2 University of.
Digital Libraries1 David Rashty. Digital Libraries2 “A library is an arsenal of liberty” Anonymous.
Topic 4 - Database Design Unit 1 – Database Analysis and Design Advanced Higher Information Systems St Kentigern’s Academy.
Post-Ranking query suggestion by diversifying search Chao Wang.
A New Algorithm for Inferring User Search Goals with Feedback Sessions.
Augmenting (personal) IR Readings Review Evaluation Papers returned & discussed Papers and Projects checkin time.
Unclassified//For Official Use Only 1 RAPID: Representation and Analysis of Probabilistic Intelligence Data Carnegie Mellon University PI : Prof. Jaime.
Identifying “Best Bet” Web Search Results by Mining Past User Behavior Author: Eugene Agichtein, Zijian Zheng (Microsoft Research) Source: KDD2006 Reporter:
Smart Web Search Agents Data Search Engines >> Information Search Agents - Traditional searching on the Web is done using one of the following three: -
Thomas Grandell April 8 th, 2016 This work is licensed under the Creative Commons Attribution 4.0 International.
Computer Science, University College Cork, Ireland A Reporting Framework for Search Session Evaluation Cathal Hoare Humphrey Sorensen.
Lecture-6 Bscshelp.com. Todays Lecture  Which Kinds of Applications Are Targeted?  Business intelligence  Search engines.
WHIM- Spring ‘10 By:-Enza Desai. What is HCIR? Study of IR techniques that brings human intelligence into search process. Coined by Gary Marchionini.
SEMINAR ON INTERNET SEARCHING PRESENTED BY:- AVIPSA PUROHIT REGD NO GUIDED BY:- Lect. ANANYA MISHRA.
Sparse Coding: A Deep Learning using Unlabeled Data for High - Level Representation Dr.G.M.Nasira R. Vidya R. P. Jaia Priyankka.
Introduction to Machine Learning, its potential usage in network area,
Understanding and Critically Appraising the Literature Review
Information Retrieval in Practice
WP5: Semantic Multimedia
Queensland University of Technology
Kyriaki Dimitriadou, Brandeis University
Multimedia Content-Based Retrieval
Kenneth Baclawski et. al. PSB /11/7 Sa-Im Shin
WXGE6103 Software Engineering Process and Practice
Information Retrieval and Web Search
Insights driven Customer Experience
What’s on Your Mind: Automatic Intent Modelling for Data Exploration
Datamining : Refers to extracting or mining knowledge from large amounts of data Applications : Market Analysis Fraud Detection Customer Retention Production.
Information Retrieval and Web Search
SIS: A system for Personal Information Retrieval and Re-Use
Submitted By: Usha MIT-876-2K11 M.Tech(3rd Sem) Information Technology
An Efficient method to recommend research papers and highly influential authors. VIRAJITHA KARNATAPU.
Athabasca University School of Computing and Information Science
Exploratory Search Beyond the Query–Response Paradigm
Martin Rajman, EPFL Switzerland & Martin Vesely, CERN Switzerland
Exploratory search: New name for an old hat?
Software engineering -1
Automating Profitable Growth™
Magnet & /facet Zheng Liang
Code search & recommendation engines
Database Management Systems
Academic & More Group 4 谢知晖 王逸雄 郭嘉宋 程若愚.
Web Mining Research: A Survey
Knowledge Sharing Mechanism in Social Networking for Learning
Interactive Information Retrieval
Presentation transcript:

Presented by Archana Kumari (31503103) | Supervised By Mr Vikram Singh Guiding the User: Feedback-driven Result Ranking and Query Refinement for Data Exploration Presented by Archana Kumari (31503103) | Supervised By Mr Vikram Singh

Overview of Research Area Data Exploration is efficiently extracting knowledge from data even if we do not know exactly what we are looking for. This notion of Data Exploration gave birth to Exploratory Search where the user iteratively and if possible interactively try to gain insights from data. Exploratory search can be used to describe an information-seeking problem context that is open-ended, persistent, and multi-faceted; and to describe information-seeking processes that are opportunistic, iterative, and multi-tactical [1]. [2] identified three facets of data exploration as shown. We will explore the User Interaction facet that includes guiding the user through the Exploratory Search Process. Data Exploration User Interaction Middleware Underlying Database

Current Status of Research Area To meet this ever growing thirst of information several tools and techniques to support Information Seeking and Searching have been implemented (like Google etc.). Much research has been conducted to carry out traditional look-up based search, navigational requests and closed informational requests. However, none of the existing systems provides the explicit functionality to support exploration. The high involvement of user and the urgent need of Understanding rather than mere Finding the information lead to the development of Exploratory Search Systems (ESS). Although a lot of theoretical research is going on ESS, the solutions are yet not efficient enough for commercialization.

Research Issues Inability of recognising precise information needs mandate the need of user assistance in formulating the queries. Understanding, Refining and Organizing search results on-the-fly as information needs evolve using feedback through out the exploratory search session since traditional keyword search systems mostly fetch relevance ranked list. Rapid, Incremental, and Reversible control of the Query and Result Sets through highly interactive Interfaces as short queries typed into search boxes are not robust enough to meet all the demands.

Existing Techniques An exploration session will include several queries where the results of each query trigger the formulation of the next one. In this setting the user does not have to be aware of the underlying schema of the database. Several advanced visualization tools and exploration interfaces have been proposed recently to aid the user in overall search process. Existing Search Systems can be broadly classified into three categories – 1. Systems assist in Query Formulation with the help of techniques like Query Recommendations and labelling relevant objects to construct exact query predicates. Data Exploration Systems Assisting Query Formulation Systems Automating Search Process Novel Query Interfaces

Existing Techniques Systems automate search process by discovering data objects that are relevant to the user using techniques such as classification based on relevance-feedback facet search techniques. Many novel interfaces have been proposed recently such as Looking Ahead [4] and Rank as you Go [3] where the aim is to provide strong visualization capabilities and more control over query predicates. The aim of these techniques is to help people understand the relationship between the documents a query will retrieve and documents already found within in a search session. This better understanding will bridge the gap between information and the information needs of the searcher.

Proposal We propose a highly interactive and user friendly Exploratory Search System visual analytic approach. Queries can be a poor representation of the information need. Short queries are often used in search engines due to the limitation of search engines few keywords per query on average. Hence limited results are obtained. Our proposed approach will help user in following ways – Helping user formulate precise queries using Query Refinement with feedback from user. Feedback driven result ranking results as earlier approach of relevance ranked listing is not flexible enough to evolve with the user interests through the timeline of search session. More control over Query and Result set with higher degree of user interaction. Features like “Keep in” , “Keep out”, “Like”, “Dislike” , selecting facets and ease of selecting desired Keywords from drop down menu will help to reduce cognitive load from the user. Strong Visualization features in the shape of bars and pie charts to measure the overlap between previous and the current iteration of the search after modifications in query., and the relative distribution of selected keywords in first 100 retrieved results Query refinement is a process of transforming a query into a new query that reflect the user information need in a higher accuracy.

Proposal GUI Mock-ups

Tools / Data Needed MySQL Database Libraries like jQuery, d3, Underscore.js IDE for PHP, HTML, JavaScript, .

Current Status of work Initial Literature Survey Problem Statement Formulation Submitted a paper on Understanding User Search Intention in Interactive Data Exploration Laying out the groundwork and preparing system for the Development of the proposed ESS

Significant References [1] Idreos S, Papaemmanouil O, Chaudhuri S. “Overview of data exploration techniques”. InProceedings of ACM SIGMOD International Conference on Management of Data 2015 pp. 277-281. ACM. [2] Marchionini G. Exploratory search: from finding to understanding. Communications of the ACM. 2006 Apr 1;49(4):41-6. [3] di Sciascio C, Sabol V, Veas EE. Rank As You Go: User-Driven Exploration of Search Results. InProceedings of the 21st International Conference on Intelligent User Interfaces 2016 Mar 7 (pp. 118-129). ACM. [4] Qvarfordt P, Golovchinsky G, Dunnigan T, Agapie E. Looking ahead: query preview in exploratory search. InProceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval 2013 Jul 28 (pp. 243-252). ACM.

Thank You Questions?