TrendsSummary: A platform for retrieving and summarizing trendy multimedia contents

Daehoon Kim, Daeyong Kim, Sanghoon Jun, Seungmin Rho, Een Jun Hwang

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

With the flood and popularity of various multimedia contents on the Internet, searching for appropriate contents and representing them effectively has become an essential part for user satisfaction. So far, many contents recommendation systems have been proposed for this purpose. A popular approach is to select hot or popular contents for recommendation using some popularity metric. Recently, various social network services (SNSs) such as Facebook and Twitter have become a widespread social phenomenon owing to the smartphone boom. Considering the popularity and user participation, SNS can be a good source for finding social interests or trends. In this study, we propose a platform called TrendsSummary for retrieving trendy multimedia contents and summarizing them. To identify trendy multimedia contents, we select candidate keywords from raw data collected from Twitter using a syntactic feature-based filtering method. Then, we merge various keyword variants based on several heuristics. Next, we select trend keywords and their related keywords from the merged candidate keywords based on term frequency and expand them semantically by referencing portal sites such as Wikipedia and Google. Based on the expanded trend keywords, we collect four types of relevant multimedia contents—TV programs, videos, news articles, and images—from various websites. The most appropriate media type for the trend keywords is determined based on a naïve Bayes classifier. After classification, appropriate contents are selected from among the contents of the selected media type. Finally, both trend keywords and their related multimedia contents are displayed for effective browsing. We implemented a prototype system and experimentally demonstrated that our scheme provides satisfactory results.

Original languageEnglish
Pages (from-to)857-872
Number of pages16
JournalMultimedia Tools and Applications
Volume73
Issue number2
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Smartphones
Recommender systems
Syntactics
Websites
Classifiers
Internet

ASJC Scopus subject areas

  • Media Technology
  • Hardware and Architecture
  • Computer Networks and Communications
  • Software

Cite this

TrendsSummary : A platform for retrieving and summarizing trendy multimedia contents. / Kim, Daehoon; Kim, Daeyong; Jun, Sanghoon; Rho, Seungmin; Hwang, Een Jun.

In: Multimedia Tools and Applications, Vol. 73, No. 2, 01.01.2014, p. 857-872.

Research output: Contribution to journalArticle

Kim, Daehoon ; Kim, Daeyong ; Jun, Sanghoon ; Rho, Seungmin ; Hwang, Een Jun. / TrendsSummary : A platform for retrieving and summarizing trendy multimedia contents. In: Multimedia Tools and Applications. 2014 ; Vol. 73, No. 2. pp. 857-872.
@article{cbf162afc50f46199bc0535b0ca85d22,
title = "TrendsSummary: A platform for retrieving and summarizing trendy multimedia contents",
abstract = "With the flood and popularity of various multimedia contents on the Internet, searching for appropriate contents and representing them effectively has become an essential part for user satisfaction. So far, many contents recommendation systems have been proposed for this purpose. A popular approach is to select hot or popular contents for recommendation using some popularity metric. Recently, various social network services (SNSs) such as Facebook and Twitter have become a widespread social phenomenon owing to the smartphone boom. Considering the popularity and user participation, SNS can be a good source for finding social interests or trends. In this study, we propose a platform called TrendsSummary for retrieving trendy multimedia contents and summarizing them. To identify trendy multimedia contents, we select candidate keywords from raw data collected from Twitter using a syntactic feature-based filtering method. Then, we merge various keyword variants based on several heuristics. Next, we select trend keywords and their related keywords from the merged candidate keywords based on term frequency and expand them semantically by referencing portal sites such as Wikipedia and Google. Based on the expanded trend keywords, we collect four types of relevant multimedia contents—TV programs, videos, news articles, and images—from various websites. The most appropriate media type for the trend keywords is determined based on a na{\"i}ve Bayes classifier. After classification, appropriate contents are selected from among the contents of the selected media type. Finally, both trend keywords and their related multimedia contents are displayed for effective browsing. We implemented a prototype system and experimentally demonstrated that our scheme provides satisfactory results.",
keywords = "Multimedia contents recommendation, Na{\"i}ve Bayes classifier, Summarization, TreeMap, Trends, Twitter",
author = "Daehoon Kim and Daeyong Kim and Sanghoon Jun and Seungmin Rho and Hwang, {Een Jun}",
year = "2014",
month = "1",
day = "1",
doi = "10.1007/s11042-013-1547-0",
language = "English",
volume = "73",
pages = "857--872",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - TrendsSummary

T2 - A platform for retrieving and summarizing trendy multimedia contents

AU - Kim, Daehoon

AU - Kim, Daeyong

AU - Jun, Sanghoon

AU - Rho, Seungmin

AU - Hwang, Een Jun

PY - 2014/1/1

Y1 - 2014/1/1

N2 - With the flood and popularity of various multimedia contents on the Internet, searching for appropriate contents and representing them effectively has become an essential part for user satisfaction. So far, many contents recommendation systems have been proposed for this purpose. A popular approach is to select hot or popular contents for recommendation using some popularity metric. Recently, various social network services (SNSs) such as Facebook and Twitter have become a widespread social phenomenon owing to the smartphone boom. Considering the popularity and user participation, SNS can be a good source for finding social interests or trends. In this study, we propose a platform called TrendsSummary for retrieving trendy multimedia contents and summarizing them. To identify trendy multimedia contents, we select candidate keywords from raw data collected from Twitter using a syntactic feature-based filtering method. Then, we merge various keyword variants based on several heuristics. Next, we select trend keywords and their related keywords from the merged candidate keywords based on term frequency and expand them semantically by referencing portal sites such as Wikipedia and Google. Based on the expanded trend keywords, we collect four types of relevant multimedia contents—TV programs, videos, news articles, and images—from various websites. The most appropriate media type for the trend keywords is determined based on a naïve Bayes classifier. After classification, appropriate contents are selected from among the contents of the selected media type. Finally, both trend keywords and their related multimedia contents are displayed for effective browsing. We implemented a prototype system and experimentally demonstrated that our scheme provides satisfactory results.

AB - With the flood and popularity of various multimedia contents on the Internet, searching for appropriate contents and representing them effectively has become an essential part for user satisfaction. So far, many contents recommendation systems have been proposed for this purpose. A popular approach is to select hot or popular contents for recommendation using some popularity metric. Recently, various social network services (SNSs) such as Facebook and Twitter have become a widespread social phenomenon owing to the smartphone boom. Considering the popularity and user participation, SNS can be a good source for finding social interests or trends. In this study, we propose a platform called TrendsSummary for retrieving trendy multimedia contents and summarizing them. To identify trendy multimedia contents, we select candidate keywords from raw data collected from Twitter using a syntactic feature-based filtering method. Then, we merge various keyword variants based on several heuristics. Next, we select trend keywords and their related keywords from the merged candidate keywords based on term frequency and expand them semantically by referencing portal sites such as Wikipedia and Google. Based on the expanded trend keywords, we collect four types of relevant multimedia contents—TV programs, videos, news articles, and images—from various websites. The most appropriate media type for the trend keywords is determined based on a naïve Bayes classifier. After classification, appropriate contents are selected from among the contents of the selected media type. Finally, both trend keywords and their related multimedia contents are displayed for effective browsing. We implemented a prototype system and experimentally demonstrated that our scheme provides satisfactory results.

KW - Multimedia contents recommendation

KW - Naïve Bayes classifier

KW - Summarization

KW - TreeMap

KW - Trends

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=84916943044&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84916943044&partnerID=8YFLogxK

U2 - 10.1007/s11042-013-1547-0

DO - 10.1007/s11042-013-1547-0

M3 - Article

AN - SCOPUS:84916943044

VL - 73

SP - 857

EP - 872

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

SN - 1380-7501

IS - 2

ER -