Design of Improved Social Event Story Board From Image Click-Through Data
Author(s):
Sahith.R, Ch. Anil Kumar, A. Venu Madhavi
Keywords:
Event storyboard, social media, click-throughdata, non-negative matrix factorization, image search.
Abstract
Traditional sites had been pushed by human edited situations which lead to big web search traffic. This paper is actually a survey conductedfor identifying the different event detection approaches that are beneficial for event mining.While traditionalsites can just present human edited functions, in this particular paper weprovide a novel system to immediately identify events from searchlog data and produce storyboards in which the events are actually arranged chronologically. We selected image search log as the source forevent mining, as search logs could even represent people's interests.In order to find happenings from log data, we show a Smooth Nonnegative Matrix Factorization framework (SNMF) that combinesthe info of query semantics, temporal correlations, research logs as well as time continuity. Additionally, we think about the time factoran essential component since many different events will build in various time tendencies. Additionally, to make a media-rich&visually attractive storyboard, each and every event is actually related with a set of representative pictures set up along a timeline. Theserelevant images are instantly selected from image search engine results by analyzing image content features. Celebrities are used by us as our test domain, that takes a great percent of image search traffics.
Article Details
Unique Paper ID: 144859

Publication Volume & Issue: Volume 4, Issue 5

Page(s): 109 - 113
Article Preview & Download


Share This Article

Join our RMS

Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Call For Paper

Volume 10 Issue 10

Last Date for paper submitting for March Issue is 25 June 2024

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews