JIST 2012

Utilizing Linked Open Data
(LOD) Resources for
Semantic Enhancement of
User-Generated Content
Dong-Po Deng1,2, Guan-Shuo Mai3, Cheng-Hsin Hsu3,
Chin-Lung Chang1,4, Tyng-Ruey Chuang1, and Kwang-Tsao Shao3

1ITC, University of Twente, Enschede, the Netherlands

2Institute of Information Science & 3Biodiversity Research Center,
Academia Sinica, Taipei, Taiwan
4Department of Computer Science and Information Engineering
National Taiwan University of Science and Technology
Taipei, Taiwan

Thursday, February 7, 2013

Outline
 Background
 Motivation
 Data Collection
 LOD resources - LODE and LOD TGN
 An approach for processing UGC
 Information Extraction
 Information Formalization
 Information Reuse
 Conclusion remarking

JIST2012 2012/12/3 2


Outline
 Background
 Motivation
 Data Collection

JIST2012 2012/12/3 3


Background
 Web 2.0 technologies enable people to contribute
their content on the web, e.g. wiki, blog, tagging
 Social media utilize web 2.0 technologies to
support social interactive on the web, e.g. twitter,
flickr, facebook
 The content on the web (or/and social media)
contributed by people is called “User-Generated
Content” (UGC)
 UGC is mainly multimedia or textual data
 UGC is considered as a potential resource for
scientific projects, e.g. citizen science

JIST2012 2012/12/3 4


Background(cont.)
 There are several problems to harvest UGC to
scientific purposes
 The unstructured UGC is difficult to handle
 The semantics of UGC is often ambiguous or/and poor
 Social media is not designed for scientific purposes

Courtesy from http://www.datenform.de/mapeng.html

JIST2012 2012/12/3 5


Outline
 Background
 Motivation
 Data Collection

JIST2012 2012/12/3 6


Motivation
 LOD datasets as resources
 LOD aims on how to make data available on the Web, and
to interconnect data with the aim of increasing its value for
users
 about 300 datasets consisting of over 31 billion RDF triples
within LOD projects.
 Each entry representing a fact in LOD datasets has
a Unique Resource Identifier (URI) which is
referenceable and linkable on the Web.
 The high interconnectivity between entries
potentially increases discoverability, reusability,
and the utility of information

JIST2012 2012/12/3 7


Motivation (cont.)
 Therefore, if named entities of UGC can be
identified and connected to entries of LOD, the
semantics of named entities would be
disambiguated, so that the UGC could be easier to
process.

JIST2012 2012/12/3 8


Outline
 Background
 Motivation
 Data Collection

JIST2012 2012/12/3 9


Data collection
 Two Facebook interest groups for ecological
observations in Taiwan

http://www.facebook.com/groups/roadkilled/ http://www.facebook.com/groups/enjoymoths/

JIST2012 2012/12/3 10


Ecological Observations on Facebook

JIST2012 2012/12/3 11


Outline
 Background
 Motivation
 Data Collection

JIST2012 2012/12/3 12


LOD Ecology
 Linked Open Data of Ecology (LODE) is a validated
dataset from a LOD project.
 LODE integrated 5 previously distributed
databases:

TFRI: Taiwan Forestry Research Institute

JIST2012 2012/12/3 13


LODE in Linked Open Data Cloud

JIST2012 2012/12/3 14


LOD Taiwan Geographic Name (TGN)
 LOD TGN is mainly transferred from Taiwan
Gazetteer via LOD principles
 LOD TGN has 159,241 geographic name entries, in
which 17,442 entries are linked to geonames.org

JIST2012 2012/12/3 15


Outline
 Background
 Motivation
 Data Collection

JIST2012 2012/12/3 16


An approach for processing UGC
Information Extraction Information Reuse

Information Formalization

JIST2012 2012/12/3 17


Outline
 Background
 Motivation
 Data Collection

JIST2012 2012/12/3 18


Problems in Chinese species names in
Facebook ecological observations

曙鳳蝶 (Atrophaneura Horishana) 曙鳳

(1) 玉帶鳳蝶 (Papilio Polytes) 玉帶

琉璃紋鳳蝶 (Papilio Hermosanus) 琉璃
Adjective Noun

細紋 (pronounced Si-Wen, meaning “fine veined”
細紋黃鉤蛾
(2) 細紋蠍蛉
細紋新蠍蛉
...15 species names with prefix name “細紋”

JIST2012 2012/12/3 19


Identifying shortened
species names

Confidence value =

JIST2012 2012/12/3 20


Determine a species name for a thread
 What if several species
names had mentioned in
one thread? We used three
criteria
 How many Like does the post or
the comments get?
 How prestigious are the people
who post or make comments?
 How many times does a species
name occur in a thread?

JIST2012 2012/12/3 21


The problems of geographic names in

An example:
The Endemic Species Research Institute
特有生物研究保育中心
Te-You-Sheng-Wu-Yan-Jiou-Bao-Yu-Jhong-Sin

is shorten to

特生中心
Te-Sheng-Jhong-Sin

JIST2012 2012/12/3 22


The problems of geographic names in

An example:
The Endemic Species Research Institute
特有生物研究保育中心
Te-You-Sheng-Wu-Yan-Jiou-Bao-Yu-Jhong-Sin

is shorten to

特生中心 There are no rules to
Te-Sheng-Jhong-Sin shorten long geographic
names

JIST2012 2012/12/3 22


Identifying shortened geographic
names

JIST2012 2012/12/3 23


The ontology...
 is relied on a Facebook thread, which is an entity
comprised of social media contents involving
peoples, places, time periods, photos, and links to
other contents
 uses standard vocabularies,
 Semantically-Interlinked Online communities (SIOC) can be
used to represent the structure of Facebook posts,
comments, and threads.
 Friend of a Friend (FOAF) can be used to describe content
creators,
 and Dublin Core for the interlinked contents they created

JIST2012 2012/12/3 24


An ontology for formalizing the extracted
information from Facebook threads

JIST2012 2012/12/3 25


Outline
 Background
 Motivation
 Data Collection

JIST2012 2012/12/3 26


Transfer ecological observations in
Facebook to RDF

http://140.109.28.64:2020/page/thread/177883715557195_440860179259546

JIST2012 2012/12/3 27


The extracted species name from the
Facebook thread is linked to LOD resources

JIST2012 2012/12/3 28


A taxon of Theretra Nessus is the
extracted species name

JIST2012 2012/12/3 29


A taxon of Theretra Nessus is the
extracted species name

This entry is connected to LODE via owl:sameAs
JIST2012 2012/12/3 29


The extracted place name from the
Facebook thread is linked to LOD resources

JIST2012 2012/12/3 30


The entry of LOD TGN transferred from
Taiwan Gazetteer

JIST2012 2012/12/3 31


The entry of LOD TGN transferred from
Taiwan Gazetteer

It is linked to geonames.org via owl:sameAs

JIST2012 2012/12/3 31


Publish the processed Facebook
ecological observations

JIST2012 2012/12/3 32


Outline
 Background
 Motivation
 Data Collection

JIST2012 2012/12/3 33


A semantic annotation plug-in for entering
geographic names in Facebook posts

JIST2012 2012/12/3 34


JIST2012 2012/12/3 35


Outline
 Background
 Motivation
 Data Collection

JIST2012 2012/12/3 36


Conclusion remarking
 This study reports our experiences in transferring FB
ecological observations to interlink to LOD
resources (LODE and LOD TGN)
 With these information extraction tools and LOD
resources, we developed a tool for semantic
enhancement of user input.

 The LOD TGN is an ongoing project.
 In the future, we will consolidate the feature types
of the geographic names, and we plan to make
the LOD TGN a geospatial semantics reference
resource.
JIST2012 2012/12/3 37


Thank you for your attentions

Questions?

deng@itc.nl

JIST2012 2012/12/3 38


JIST 2012

More Related Content

Viewers also liked (10)

Similar to JIST 2012 (20)

More from Dongpo Deng (20)

JIST 2012