DevoxxFR 2024 Reproducible Builds with Apache Maven
2012 ACM Geocrowd
1. &
Academia Sinica
Using Social Media for Collaborative
Species Identification and Occurrence:
Issues, Methods, and Tools
Dongpo Deng, G.-S. Mai, C.-H. Hsu, T.-R. Chuang,
T.-E. Lin, H.-H. Lin, K.-T. Shao, R. Lemmens, M.-J.
Kraak
!
Faculty of Geo-Information Science and Earth Observation (ITC),
University of Twente, the Netherlands
&
Institute of Information Science, and Biodiversity Research
Center,
Academia Sinica, Taiwan
&
Endemic Species Research Institute,
Council of Agriculture, Taiwan
ACM SIGSpatial GeoCrowd, 5 Nov. 2012
2. Background
! A large number of social media users as human
senors actively report what are happening in their
surroundings.
! Voluntary participation has become an important
part of citizen science. The emergence of social
media offers new opportunities to recruit more
participants to citizen science projects.
! Utilizing social media to engage with a large
number of people can be a way to improve data
collection over a large geographic region and a
long time span.
Institute of Information Science, Academia Sinica
ACM SIGSpatial GeoCrowd
2012/11/6
2
5. Motivations
! The transformation from crowdsourced information
to citizen science is a problem
! There is no social media specifically designed for citizen
science.
! Social media applications and services facilitate social
interactions, but not scientific activities and data analyses.
! The crowdsourced information contributed by netizens
through social media is often in unstructured data format
such as text and image.
! It is a challenge to process unstructured data
collections for scientific purposes.
Institute of Information Science, Academia Sinica
ACM SIGSpatial GeoCrowd
2012/11/6
5
6. Institutional GI and UGGC
Institutional GI
User Generated Geo Content!
(Volunteered Geographic Information)
Unstructured GI
Structured GI
Institute of Information Science, Academia Sinica
ACM SIGSpatial GeoCrowd
2012/11/6
7. Research questions and purposes
! Research questions
! Can social media be a tool for citizen science project?
! How to deal with unstructured data from social media?
! How to use the structured (processed) crowdsourced
information to help participants of citizen science projects?
! Research purposes
! To discuss whether social media can be a tool for citizen
science
! To provide an approach for processing unstructured data
from social media
! To develop tools for processing information from social
media, and reuse the processed information for citizens and
scientists
Institute of Information Science, Academia Sinica
ACM SIGSpatial GeoCrowd
2012/11/6
7
8. Ecological Observation on Facebook
http://www.facebook.com/groups/enjoymoths/permalink/438916509453913/
Institute of Information Science, Academia Sinica
ACM SIGSpatial GeoCrowd
2012/11/6
8
9. An approach for processing
crowdsourced information
Information Reuse
Information Extraction
Information Formalization
Institute of Information Science, Academia Sinica
ACM SIGSpatial GeoCrowd
2012/11/6
9
10. Identifying shortened species names
Confidence value =
Institute of Information Science, Academia Sinica
ACM SIGSpatial GeoCrowd
2012/11/6
10
11. Identifying shortened place names
Institute of Information Science, Academia Sinica
ACM SIGSpatial GeoCrowd
2012/11/6
11
12. An ontology for formalizing the extracted
information from Facebook threads
Institute of Information Science, Academia Sinica
ACM SIGSpatial GeoCrowd
2012/11/6
12
13. Publish the processed crowdsourced
information
http://140.109.28.64:2020/page/thread/177883715557195_438916509453913
Institute of Information Science, Academia Sinica
ACM SIGSpatial GeoCrowd
2012/11/6
13
14. The entry for the extracted species
name
Institute of Information Science, Academia Sinica
ACM SIGSpatial GeoCrowd
2012/11/6
14
15. The entry for the extracted geographic
name
Institute of Information Science, Academia Sinica
ACM SIGSpatial GeoCrowd
2012/11/6
15
16. Use CMS to manage processed data
http://roadkilled.biota.biodiv.tw
http://enjoymoths.biodiv.tw/
Institute of Information Science, Academia Sinica
ACM SIGSpatial GeoCrowd
2012/11/6
16
17. A semantic annotation plug-in for entering
geographic names in Facebook posts
Institute of Information Science, Academia Sinica
ACM SIGSpatial GeoCrowd
2012/11/6
17
19. Conclusion and future works
! This study proposed an approach to transferring
unstructured crowdsourced information to structured
data for scientific purposes
! We believe it has broader application in UGC
management as well, and it promises to be a good
start in solving important design problems in citizen
science projects on the Web
! In the future, we will improve these tools and
investigate new ways to apply them in other contexts
! Also, we will apply the crowdsourced data collected
from Facebook to ecological researches such as the
hotspot of roadkill
Institute of Information Science, Academia Sinica
ACM SIGSpatial GeoCrowd
2012/11/6
19