東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Social user mining: User profiling o...

Eltaher, Mohammed Ali.

FindBook

Google Book

Amazon

博客來

Social user mining: User profiling of social media network based on multimedia data mining.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Social user mining: User profiling of social media network based on multimedia data mining./
作者:	Eltaher, Mohammed Ali.
面頁冊數:	93 p.
附註:	Source: Dissertation Abstracts International, Volume: 76-10(E), Section: B.
Contained By:	Dissertation Abstracts International76-10B(E).
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3704326
ISBN:	9781321766493

Social user mining: User profiling of social media network based on multimedia data mining.
Eltaher, Mohammed Ali.

Social user mining: User profiling of social media network based on multimedia data mining. - 93 p.

Source: Dissertation Abstracts International, Volume: 76-10(E), Section: B.

Thesis (Ph.D.)--University of Bridgeport, 2015.

In recent years, the pervasive use of social media has generated extraordinary amounts of data that has started to gain an increasing amount of attention. Each social media source utilizes different data types such as textual and visual. For example, Twitter is used to transmit short text messages, whereas Flickr is used to convey images and videos. Moreover, Facebook uses all of these data types. From the social media users' standpoint, it is highly desirable to find patterns from different data formats.

ISBN: 9781321766493Subjects--Topical Terms:

523869
Computer science.

Social user mining: User profiling of social media network based on multimedia data mining.
LDR:03425nmm a2200313 4500 001 2066601
005 20151205153416.5
008 170521s2015 ||||||||||||||||| ||eng d
020 $a 9781321766493
035 $a (MiAaPQ)AAI3704326
035 $a AAI3704326
040 $a MiAaPQ $c MiAaPQ
100 1 $a Eltaher, Mohammed Ali. $3 3181423
245 1 0 $a Social user mining: User profiling of social media network based on multimedia data mining.
300 $a 93 p.
500 $a Source: Dissertation Abstracts International, Volume: 76-10(E), Section: B.
500 $a Adviser: Jeongkyu Lee.
502 $a Thesis (Ph.D.)--University of Bridgeport, 2015.
520 $a In recent years, the pervasive use of social media has generated extraordinary amounts of data that has started to gain an increasing amount of attention. Each social media source utilizes different data types such as textual and visual. For example, Twitter is used to transmit short text messages, whereas Flickr is used to convey images and videos. Moreover, Facebook uses all of these data types. From the social media users' standpoint, it is highly desirable to find patterns from different data formats.
520 $a The result of the huge amount of data from different sources or types has provided many opportunities for researchers in the fields of data mining and data analytics. Not only the methods and tools to organize and manage such data have become extremely important, but also methods and tools to discover hidden knowledge from such data, which can be used for a variety of applications. For example, the mining of a user's profile on social media could help to discover any missing information, including the user's location or gender information. However, the task of developing such methods and tools is very challenging. Social media data is unstructured and different from traditional data because of its privacy settings, data noise, and large capacity of data. Moreover, combining image features and text information annotated by users reveals interesting properties of social user mining, and serves as a useful tool for discovering unknown information about the users. Minimal research has been conducted on the combination of image and text data for social user mining.
520 $a To address these challenges and to discover unknown information about users, we proposed a novel mining framework for social user mining that includes: 1) a data assemble module for different media source, 2) a data integration module, and 3) mining applications. First, we introduced a data assemble module in order to process both the textual and the visual information from different media sources, and evaluated the appropriate multimedia features for social user mining. Then, we proposed a new data integration method in order to integrate the textual and the visual data. Unlike the previous approaches that used a content based approach to merge multiple types of features, our main approach is based on image semantics through a semi-automatic image tagging system. Lastly, we presented two different application as an example of social user mining, gender classification and user location.
590 $a School code: 0749.
650 4 $a Computer science. $3 523869
650 4 $a Computer engineering. $3 621879
650 4 $a Mining engineering. $3 788403
690 $a 0984
690 $a 0464
690 $a 0551
710 2 $a University of Bridgeport. $b Computer Science and Engineering. $3 3181424
773 0 $t Dissertation Abstracts International $g 76-10B(E).
790 $a 0749
791 $a Ph.D.
792 $a 2015
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3704326