SlideShare une entreprise Scribd logo
1  sur  33
Conceptual Design
toward a Visualization System of
University’s Web Presence
Simple Analysis and System Development Using Twitter
MIHO FUNAMORI, NATIONAL INSTITUTE OF INFORMATICS
MASAO MORI, TOKYO INSTITUTE OF TECHNOLOGY
Today’s Talk
 Background Issue
 Study
1. System Concept
2. Systematic Tweets Analysis
3. Manual Analysis
 Discussion
1
Background Issue
The Mode Changes of University Reputation Management
in the Digital Age
University Reputation
in the Past
 Established Status
 SAT, ACT, 偏差値
 University Rankings
3
Managing University Reputation
is important!
Rumors can affect choice of universities!
4
Social Perception can affect
the university business
It may affect:
 Enrollment number
 University Rankings
 Funding
 Research Collaboration and Funding
 External Relations
5
Branding Strategies
in the Physical World
which basically
just imposes
certain IMAGE!
6
Reputation in the Digitized World
7
PHYSICAL
 Established
 Almost fixed
 University-based
 Macroscopic
 Limited Reach
DIGITAL
 Fluid
 Changes frequently
 Event-driven
 Microscopic
 Global Reach
Two different Reputations
8
PHYSICAL
 Printed References
 Interviews
 Questionnaire
DIGITAL
Go Internet!
How to survey
the two different Reputations
Much Work
Taking time
Expensive
… Still not representing the
whole picture
Moderate Work
Swift
Inexpensive
Not representing everything,
but showing digital aspects
9
System Concept
Visualization System of University’s Web Presence
Visualization System of
University’s Web Presence (VUWP)
Personal Comments
Profile of Senders
(Twitter, Facebook,
Blog, etc.)
University’s Web Presence
(by several aspects,
real time, visual)
1. Sorting comments by its
content and profile of
sender
2. Extract university
characteristics by different
aspects
11
University Web Presence
in Twitter
12
Estimated User of VUWP
 University Administration
 Check the social perception towards the
university
 Identify marketing points
 General People and Prospective
Students
 Check the university’s vividness
 (Accountability Purpose)
13
System Requirement:
INPUT
 Input data
 Personal comments
 Profile of senders
 Sent time of the comments, etc.
 Comments mainly on the SNS
used
 Twitter, Facebook, blogs
14
System Requirement:
ANALYSIS
 Social perception towards the
university is extracted:
 Real-time
 Quantitatively
 People’s impression towards
university is:
 Expressed qualitatively
15
System Requirement:
OUTPUT
 Output should be:
 Visual
 Easy-to-understand manner
 Clear and simple
 To let prospective students
choose university:
 Function to compare universities
16
UNIV RANKINGS
 Works mostly for Top
Universities
 Numerical measures
 Updated once a year
and expensive
VUWP
 Works also for middle
and lower-ranked
universities
 Expresses social
perceptions
 Real time and
inexpensive
Feature of VUWP
17
Systematic Tweets Analysis
Visualization System of University’s Web Presence
Methodology of
Systematic Tweets Analysis
 Use the 1000 newest tweets of
certain Japanese university
 Term Frequency Analysis
 Consider 1000 tweets as one document
and count the appearance of the words
 Tem Specificity Analysis
 Use TF-IDF method
 Obtain relative specificity of words for
respective university
19
TF-IDF method
Term Frequency – Inverse Document Frequency
 Term Frequency

 Document Frequency

 TF-IDF value

(w: word, d: document, #: count)
𝑑𝑓𝑤 = # 𝑑 ∈ 𝐷 𝑤 appears in 𝑑}
𝑡𝑓𝑖𝑑𝑓𝑤,𝑑 = 𝑡𝑓𝑤,𝑑 × log(
#𝐷
𝑑𝑓𝑤
)
20
𝑡𝑓𝑤,𝑑 = the number of 𝑤′
s appearance in 𝑑
Fix the set of Documents D
Preparation:
Morphological analysis
1. Removes emoticons, such as (^o^),
from the document.
2. Morphological analysis
 Decomposes sentences into minimal
significant linguistic elements and classifies the
elements.
 Picks up nouns, adjectives, and verbs which
are independent words
 Independent words: Words having proper meanings for itself.
21
Example of analyzing frequency and specificity of tweets
for national universities
22
Example of analyzing frequency and specificity of tweets
for private universities
23
Analysis of frequent and specific
terms for national universities
Categories
Examples remarkable frequent &
specific terms
University
Academic matters
菌 (germ)
ピロリ (pylori)
Hokkaido University
ノーベル (Nobel),
天野 (name of Nobelist)
Nagoya University
小惑星 (asteroid),
惑星 (planet)
Kyushu University
Social matters
原発 (nuclear plant),
事故 (accident)
Tohoku University
皇族 (royal family),
秋篠宮 (one of royal family)
Ochanomizu University
中核 (student movement’s name),
日教組 (union of teachers)
Kyoto University
宗教 (religion),
実現 (realization)
Osaka University
Student life
スキー (ski),
弓道 (archery)
Hitotsubashi University
合コン (party)
Tokyo Institute of Technology
General university
matters
東京理科大学, 東京電機大学, etc.,
(series of rival university names)
早稲田大学, 東京外国語大学,etc.,
(series of rival university names)
Hitotsubashi University
24
Technical Remarks
1. Need to have a dictionary of emoticons.
2. Need to have the news histories of various
concurrent events at all times.
3. Need to compare the historically fixed ideas
and image of the university to the analysis
result.
4. Need to decide whether to include
automatic tweets or not.
25
Manual Tweets Analysis
Visualization System of University’s Web Presence
Manual Tweets Analysis
1. Categorizing the Tweets
2. Deriving University Characteristic
Aspects
27
Categorizing the tweets
 Academic Matter
 Social Matter
 General Matter
 Student Life
 Other
28
Categorizing the tweets
in detail
Content of Tweets Sender
Student
life
Student clubs, other student activities Enrolled students
Entrance exams
Prospective students,
Enrolled students,
General Public
Academic
matters
Research achievements
Staff members,
Research labs,
The University
international meetings, academic conference,
departmental events, lab activities
Staff members,
Enrolled students
Faculty recruitment Staff members
General
University
matters
Official tweets by the University The University
Day-to-day tweets
Staff members,
Enrolled students
Campus scenery, events
Visitors,
Enrolled students
Social
matters
Social issues Staff members
Media coverage Mass media
The University, staff members General public
Re-tweets of university-related tweets General public
Serious incidents the university has caused
Mass media,
General public,
Staff members
Other
Not classifiable tweets ―
Calumny, abuse General public
―
Alumni
Member of University 29
University Characteristic Aspects
derived from Tweets
Activeness Popularity
・Public Relations
・Academic Outreach
・Academic activity
・Student life
・Social Outreach
・Selectivity of university
・Social attention
・Community-based
・General activity
・Jealousness
30
Next Steps
1. To find associations or rules between
the five categories and ten aspects.
2. To clarify the methodology in order to
refine the associations or rules by
machine learning.
3. To specify the evaluation method of
the above methodology.
31
Future Work
 Extend the analysis to other SNS
such as Facebook or Blogs.
 Twitter is difficult to specify the user
profile.
32

Contenu connexe

Tendances

OWD2012 - 2,3 - Studiesucces verhogen met learging analytics - Mykola Pecheni...
OWD2012 - 2,3 - Studiesucces verhogen met learging analytics - Mykola Pecheni...OWD2012 - 2,3 - Studiesucces verhogen met learging analytics - Mykola Pecheni...
OWD2012 - 2,3 - Studiesucces verhogen met learging analytics - Mykola Pecheni...
SURF Events
 
Symplicity Symposium 2015 Reporting Presentation Rev FINAL
Symplicity Symposium 2015 Reporting Presentation Rev FINALSymplicity Symposium 2015 Reporting Presentation Rev FINAL
Symplicity Symposium 2015 Reporting Presentation Rev FINAL
Ron Gaschler
 
Victor (Shengli) Sheng
Victor (Shengli) ShengVictor (Shengli) Sheng
Victor (Shengli) Sheng
butest
 

Tendances (20)

Education data mining presentation
Education data mining presentationEducation data mining presentation
Education data mining presentation
 
OWD2012 - 2,3 - Studiesucces verhogen met learging analytics - Mykola Pecheni...
OWD2012 - 2,3 - Studiesucces verhogen met learging analytics - Mykola Pecheni...OWD2012 - 2,3 - Studiesucces verhogen met learging analytics - Mykola Pecheni...
OWD2012 - 2,3 - Studiesucces verhogen met learging analytics - Mykola Pecheni...
 
Symplicity Symposium 2015 Reporting Presentation Rev FINAL
Symplicity Symposium 2015 Reporting Presentation Rev FINALSymplicity Symposium 2015 Reporting Presentation Rev FINAL
Symplicity Symposium 2015 Reporting Presentation Rev FINAL
 
Introduction to the Telecom Forum Course
Introduction to the Telecom Forum CourseIntroduction to the Telecom Forum Course
Introduction to the Telecom Forum Course
 
S ta r chart
S ta r chartS ta r chart
S ta r chart
 
Final year project presentation, University of Jaffna
Final year project presentation, University of JaffnaFinal year project presentation, University of Jaffna
Final year project presentation, University of Jaffna
 
Applicability of Educational Data Mining in Afghanistan: Opportunities and Ch...
Applicability of Educational Data Mining in Afghanistan: Opportunities and Ch...Applicability of Educational Data Mining in Afghanistan: Opportunities and Ch...
Applicability of Educational Data Mining in Afghanistan: Opportunities and Ch...
 
Application of Higher Education System for Predicting Student Using Data mini...
Application of Higher Education System for Predicting Student Using Data mini...Application of Higher Education System for Predicting Student Using Data mini...
Application of Higher Education System for Predicting Student Using Data mini...
 
Comnet teaching and curriculum development processes
Comnet teaching and curriculum development processesComnet teaching and curriculum development processes
Comnet teaching and curriculum development processes
 
COMNET as a Capacity-Building Partner for Two African Institutions
COMNET as a Capacity-Building Partner for Two African InstitutionsCOMNET as a Capacity-Building Partner for Two African Institutions
COMNET as a Capacity-Building Partner for Two African Institutions
 
Software Radio Course
Software Radio CourseSoftware Radio Course
Software Radio Course
 
Introduction to Data Science - Week 2 - Predictive Analytics
Introduction to Data Science - Week 2 - Predictive AnalyticsIntroduction to Data Science - Week 2 - Predictive Analytics
Introduction to Data Science - Week 2 - Predictive Analytics
 
JIBS 2009 Bibliometrics And The REF 2009-11-13
JIBS 2009 Bibliometrics And The REF 2009-11-13JIBS 2009 Bibliometrics And The REF 2009-11-13
JIBS 2009 Bibliometrics And The REF 2009-11-13
 
Doctorate in information technology
Doctorate in information technologyDoctorate in information technology
Doctorate in information technology
 
Victor (Shengli) Sheng
Victor (Shengli) ShengVictor (Shengli) Sheng
Victor (Shengli) Sheng
 
Predicting instructor performance using data mining techniques in higher educ...
Predicting instructor performance using data mining techniques in higher educ...Predicting instructor performance using data mining techniques in higher educ...
Predicting instructor performance using data mining techniques in higher educ...
 
La tartu
La tartuLa tartu
La tartu
 
Edld 5352ppt[1]
Edld 5352ppt[1]Edld 5352ppt[1]
Edld 5352ppt[1]
 
2019 DSA 105 Introduction to Data Science Week 3
2019 DSA 105 Introduction to Data Science Week 32019 DSA 105 Introduction to Data Science Week 3
2019 DSA 105 Introduction to Data Science Week 3
 
S ta r chart presentation
S ta r chart presentationS ta r chart presentation
S ta r chart presentation
 

En vedette (10)

O mundo legal de juju - cidadania se aprende desde de formiga
O mundo legal de juju - cidadania se aprende desde de formigaO mundo legal de juju - cidadania se aprende desde de formiga
O mundo legal de juju - cidadania se aprende desde de formiga
 
Safwan-CV
Safwan-CVSafwan-CV
Safwan-CV
 
Mala
MalaMala
Mala
 
Las funciones sociales de la educación
Las funciones sociales de la educaciónLas funciones sociales de la educación
Las funciones sociales de la educación
 
Semiotica
SemioticaSemiotica
Semiotica
 
Inventions of the 1960
Inventions of the 1960Inventions of the 1960
Inventions of the 1960
 
Crash essay
Crash essayCrash essay
Crash essay
 
Atividades sobre advérbios
Atividades sobre advérbiosAtividades sobre advérbios
Atividades sobre advérbios
 
Atividades Diagnósticas - 3º ano
Atividades Diagnósticas - 3º anoAtividades Diagnósticas - 3º ano
Atividades Diagnósticas - 3º ano
 
Gênero Textual Receita
Gênero Textual ReceitaGênero Textual Receita
Gênero Textual Receita
 

Similaire à Dsir2016 vuwp

Assignment 1 Theories of LeadershipDue Week 4 and worth 150 p.docx
Assignment 1 Theories of LeadershipDue Week 4 and worth 150 p.docxAssignment 1 Theories of LeadershipDue Week 4 and worth 150 p.docx
Assignment 1 Theories of LeadershipDue Week 4 and worth 150 p.docx
sherni1
 
Chennai-PPT-3-Key Components of OBE-RVR-08-06-2018.pptx
Chennai-PPT-3-Key Components of OBE-RVR-08-06-2018.pptxChennai-PPT-3-Key Components of OBE-RVR-08-06-2018.pptx
Chennai-PPT-3-Key Components of OBE-RVR-08-06-2018.pptx
Abhishek pradeep
 

Similaire à Dsir2016 vuwp (20)

Irjet v4 i73A Survey on Student’s Academic Experiences using Social Media Data53
Irjet v4 i73A Survey on Student’s Academic Experiences using Social Media Data53Irjet v4 i73A Survey on Student’s Academic Experiences using Social Media Data53
Irjet v4 i73A Survey on Student’s Academic Experiences using Social Media Data53
 
Research sgd-madam-2015-14-mar-2015
Research sgd-madam-2015-14-mar-2015Research sgd-madam-2015-14-mar-2015
Research sgd-madam-2015-14-mar-2015
 
Sub1557
Sub1557Sub1557
Sub1557
 
Ic serv japan 20131016 v2
Ic serv japan 20131016 v2Ic serv japan 20131016 v2
Ic serv japan 20131016 v2
 
Social Phrases Having Impact in Altmetrics - SOPHIA
Social Phrases Having Impact in Altmetrics - SOPHIASocial Phrases Having Impact in Altmetrics - SOPHIA
Social Phrases Having Impact in Altmetrics - SOPHIA
 
Assignment 1 Theories of LeadershipDue Week 4 and worth 150 p.docx
Assignment 1 Theories of LeadershipDue Week 4 and worth 150 p.docxAssignment 1 Theories of LeadershipDue Week 4 and worth 150 p.docx
Assignment 1 Theories of LeadershipDue Week 4 and worth 150 p.docx
 
IT-era-Syllabus-dox-for-school-purposes-
IT-era-Syllabus-dox-for-school-purposes-IT-era-Syllabus-dox-for-school-purposes-
IT-era-Syllabus-dox-for-school-purposes-
 
MyUOC: A New Solution for Creating Versatile Learning Environments (presented...
MyUOC: A New Solution for Creating Versatile Learning Environments (presented...MyUOC: A New Solution for Creating Versatile Learning Environments (presented...
MyUOC: A New Solution for Creating Versatile Learning Environments (presented...
 
Knowledge Management for SME in the Network Society: Comparison Japan - France
Knowledge Management for SME in the Network Society: Comparison Japan - FranceKnowledge Management for SME in the Network Society: Comparison Japan - France
Knowledge Management for SME in the Network Society: Comparison Japan - France
 
Key Components of OBE for NBA and preparing Course file
Key Components of OBE for NBA and preparing Course fileKey Components of OBE for NBA and preparing Course file
Key Components of OBE for NBA and preparing Course file
 
Competency model for
Competency model forCompetency model for
Competency model for
 
Visualizing Data: Infographic Assignments across the Social Work Curriculum
Visualizing Data: Infographic Assignments across the Social Work CurriculumVisualizing Data: Infographic Assignments across the Social Work Curriculum
Visualizing Data: Infographic Assignments across the Social Work Curriculum
 
Concept Mapping in Interaction Design
Concept Mapping in Interaction DesignConcept Mapping in Interaction Design
Concept Mapping in Interaction Design
 
research methodogy
research methodogyresearch methodogy
research methodogy
 
Intute Virtual Training Suite: LILAC 2009
Intute Virtual Training Suite: LILAC 2009Intute Virtual Training Suite: LILAC 2009
Intute Virtual Training Suite: LILAC 2009
 
Chennai-PPT-3-Key Components of OBE-RVR-08-06-2018.pptx
Chennai-PPT-3-Key Components of OBE-RVR-08-06-2018.pptxChennai-PPT-3-Key Components of OBE-RVR-08-06-2018.pptx
Chennai-PPT-3-Key Components of OBE-RVR-08-06-2018.pptx
 
Smart SE: Recurrent Education Program of IoT and AI for Business
Smart SE: Recurrent Education Program of IoT and AI for BusinessSmart SE: Recurrent Education Program of IoT and AI for Business
Smart SE: Recurrent Education Program of IoT and AI for Business
 
Introductory PPT CSC202 SECURITY ARCHITECTURE.pptx
Introductory PPT CSC202 SECURITY ARCHITECTURE.pptxIntroductory PPT CSC202 SECURITY ARCHITECTURE.pptx
Introductory PPT CSC202 SECURITY ARCHITECTURE.pptx
 
#Edu14 Seminar on the State of Social Media in Higher Ed
#Edu14 Seminar on the State of Social Media in Higher Ed#Edu14 Seminar on the State of Social Media in Higher Ed
#Edu14 Seminar on the State of Social Media in Higher Ed
 
An Introduction to Information Retrieval and Applications
 An Introduction to Information Retrieval and Applications An Introduction to Information Retrieval and Applications
An Introduction to Information Retrieval and Applications
 

Plus de Masao Mori

Plus de Masao Mori (11)

H28 08-27 産学連携学会 第4回研究会(1h)
H28 08-27 産学連携学会 第4回研究会(1h)H28 08-27 産学連携学会 第4回研究会(1h)
H28 08-27 産学連携学会 第4回研究会(1h)
 
オーブンデータによる大学Ir情報システムの可能性 プレゼン資料
オーブンデータによる大学Ir情報システムの可能性 プレゼン資料オーブンデータによる大学Ir情報システムの可能性 プレゼン資料
オーブンデータによる大学Ir情報システムの可能性 プレゼン資料
 
国際観光コンベンションシンポジウム2016
国際観光コンベンションシンポジウム2016国際観光コンベンションシンポジウム2016
国際観光コンベンションシンポジウム2016
 
Logic ds-ir
Logic ds-irLogic ds-ir
Logic ds-ir
 
MJIR岡山講習会ーIRデータマネジメント20150715
MJIR岡山講習会ーIRデータマネジメント20150715MJIR岡山講習会ーIRデータマネジメント20150715
MJIR岡山講習会ーIRデータマネジメント20150715
 
東工大情報活用IR室に関する講演資料
東工大情報活用IR室に関する講演資料東工大情報活用IR室に関する講演資料
東工大情報活用IR室に関する講演資料
 
日本教育情報学会第31回年会プレゼン
日本教育情報学会第31回年会プレゼン日本教育情報学会第31回年会プレゼン
日本教育情報学会第31回年会プレゼン
 
H28.2.19 erms研究会 大学経営の鍵となるir
H28.2.19 erms研究会 大学経営の鍵となるirH28.2.19 erms研究会 大学経営の鍵となるir
H28.2.19 erms研究会 大学経営の鍵となるir
 
20150916 researchmapシンポジウム資料
20150916 researchmapシンポジウム資料20150916 researchmapシンポジウム資料
20150916 researchmapシンポジウム資料
 
平成27年11月9日 大学監査協会講演資料
平成27年11月9日 大学監査協会講演資料平成27年11月9日 大学監査協会講演資料
平成27年11月9日 大学監査協会講演資料
 
平成27年9月29日 大学監査協会講演資料
平成27年9月29日 大学監査協会講演資料平成27年9月29日 大学監査協会講演資料
平成27年9月29日 大学監査協会講演資料
 

Dernier

Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
ZurliaSoop
 
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts ServiceCall Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
MarinCaroMartnezBerg
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
amitlee9823
 
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
amitlee9823
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
amitlee9823
 

Dernier (20)

Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFx
 
BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptx
 
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
 
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts ServiceCall Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
 
Capstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics ProgramCapstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics Program
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
 
ELKO dropshipping via API with DroFx.pptx
ELKO dropshipping via API with DroFx.pptxELKO dropshipping via API with DroFx.pptx
ELKO dropshipping via API with DroFx.pptx
 
ALSO dropshipping via API with DroFx.pptx
ALSO dropshipping via API with DroFx.pptxALSO dropshipping via API with DroFx.pptx
ALSO dropshipping via API with DroFx.pptx
 
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdfAccredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
 
Sampling (random) method and Non random.ppt
Sampling (random) method and Non random.pptSampling (random) method and Non random.ppt
Sampling (random) method and Non random.ppt
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
 
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort ServiceBDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
 
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
 
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
 
VidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptxVidaXL dropshipping via API with DroFx.pptx
VidaXL dropshipping via API with DroFx.pptx
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and Milvus
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysis
 

Dsir2016 vuwp

  • 1. Conceptual Design toward a Visualization System of University’s Web Presence Simple Analysis and System Development Using Twitter MIHO FUNAMORI, NATIONAL INSTITUTE OF INFORMATICS MASAO MORI, TOKYO INSTITUTE OF TECHNOLOGY
  • 2. Today’s Talk  Background Issue  Study 1. System Concept 2. Systematic Tweets Analysis 3. Manual Analysis  Discussion 1
  • 3. Background Issue The Mode Changes of University Reputation Management in the Digital Age
  • 4. University Reputation in the Past  Established Status  SAT, ACT, 偏差値  University Rankings 3
  • 5. Managing University Reputation is important! Rumors can affect choice of universities! 4
  • 6. Social Perception can affect the university business It may affect:  Enrollment number  University Rankings  Funding  Research Collaboration and Funding  External Relations 5
  • 7. Branding Strategies in the Physical World which basically just imposes certain IMAGE! 6
  • 8. Reputation in the Digitized World 7
  • 9. PHYSICAL  Established  Almost fixed  University-based  Macroscopic  Limited Reach DIGITAL  Fluid  Changes frequently  Event-driven  Microscopic  Global Reach Two different Reputations 8
  • 10. PHYSICAL  Printed References  Interviews  Questionnaire DIGITAL Go Internet! How to survey the two different Reputations Much Work Taking time Expensive … Still not representing the whole picture Moderate Work Swift Inexpensive Not representing everything, but showing digital aspects 9
  • 11. System Concept Visualization System of University’s Web Presence
  • 12. Visualization System of University’s Web Presence (VUWP) Personal Comments Profile of Senders (Twitter, Facebook, Blog, etc.) University’s Web Presence (by several aspects, real time, visual) 1. Sorting comments by its content and profile of sender 2. Extract university characteristics by different aspects 11
  • 14. Estimated User of VUWP  University Administration  Check the social perception towards the university  Identify marketing points  General People and Prospective Students  Check the university’s vividness  (Accountability Purpose) 13
  • 15. System Requirement: INPUT  Input data  Personal comments  Profile of senders  Sent time of the comments, etc.  Comments mainly on the SNS used  Twitter, Facebook, blogs 14
  • 16. System Requirement: ANALYSIS  Social perception towards the university is extracted:  Real-time  Quantitatively  People’s impression towards university is:  Expressed qualitatively 15
  • 17. System Requirement: OUTPUT  Output should be:  Visual  Easy-to-understand manner  Clear and simple  To let prospective students choose university:  Function to compare universities 16
  • 18. UNIV RANKINGS  Works mostly for Top Universities  Numerical measures  Updated once a year and expensive VUWP  Works also for middle and lower-ranked universities  Expresses social perceptions  Real time and inexpensive Feature of VUWP 17
  • 19. Systematic Tweets Analysis Visualization System of University’s Web Presence
  • 20. Methodology of Systematic Tweets Analysis  Use the 1000 newest tweets of certain Japanese university  Term Frequency Analysis  Consider 1000 tweets as one document and count the appearance of the words  Tem Specificity Analysis  Use TF-IDF method  Obtain relative specificity of words for respective university 19
  • 21. TF-IDF method Term Frequency – Inverse Document Frequency  Term Frequency   Document Frequency   TF-IDF value  (w: word, d: document, #: count) 𝑑𝑓𝑤 = # 𝑑 ∈ 𝐷 𝑤 appears in 𝑑} 𝑡𝑓𝑖𝑑𝑓𝑤,𝑑 = 𝑡𝑓𝑤,𝑑 × log( #𝐷 𝑑𝑓𝑤 ) 20 𝑡𝑓𝑤,𝑑 = the number of 𝑤′ s appearance in 𝑑 Fix the set of Documents D
  • 22. Preparation: Morphological analysis 1. Removes emoticons, such as (^o^), from the document. 2. Morphological analysis  Decomposes sentences into minimal significant linguistic elements and classifies the elements.  Picks up nouns, adjectives, and verbs which are independent words  Independent words: Words having proper meanings for itself. 21
  • 23. Example of analyzing frequency and specificity of tweets for national universities 22
  • 24. Example of analyzing frequency and specificity of tweets for private universities 23
  • 25. Analysis of frequent and specific terms for national universities Categories Examples remarkable frequent & specific terms University Academic matters 菌 (germ) ピロリ (pylori) Hokkaido University ノーベル (Nobel), 天野 (name of Nobelist) Nagoya University 小惑星 (asteroid), 惑星 (planet) Kyushu University Social matters 原発 (nuclear plant), 事故 (accident) Tohoku University 皇族 (royal family), 秋篠宮 (one of royal family) Ochanomizu University 中核 (student movement’s name), 日教組 (union of teachers) Kyoto University 宗教 (religion), 実現 (realization) Osaka University Student life スキー (ski), 弓道 (archery) Hitotsubashi University 合コン (party) Tokyo Institute of Technology General university matters 東京理科大学, 東京電機大学, etc., (series of rival university names) 早稲田大学, 東京外国語大学,etc., (series of rival university names) Hitotsubashi University 24
  • 26. Technical Remarks 1. Need to have a dictionary of emoticons. 2. Need to have the news histories of various concurrent events at all times. 3. Need to compare the historically fixed ideas and image of the university to the analysis result. 4. Need to decide whether to include automatic tweets or not. 25
  • 27. Manual Tweets Analysis Visualization System of University’s Web Presence
  • 28. Manual Tweets Analysis 1. Categorizing the Tweets 2. Deriving University Characteristic Aspects 27
  • 29. Categorizing the tweets  Academic Matter  Social Matter  General Matter  Student Life  Other 28
  • 30. Categorizing the tweets in detail Content of Tweets Sender Student life Student clubs, other student activities Enrolled students Entrance exams Prospective students, Enrolled students, General Public Academic matters Research achievements Staff members, Research labs, The University international meetings, academic conference, departmental events, lab activities Staff members, Enrolled students Faculty recruitment Staff members General University matters Official tweets by the University The University Day-to-day tweets Staff members, Enrolled students Campus scenery, events Visitors, Enrolled students Social matters Social issues Staff members Media coverage Mass media The University, staff members General public Re-tweets of university-related tweets General public Serious incidents the university has caused Mass media, General public, Staff members Other Not classifiable tweets ― Calumny, abuse General public ― Alumni Member of University 29
  • 31. University Characteristic Aspects derived from Tweets Activeness Popularity ・Public Relations ・Academic Outreach ・Academic activity ・Student life ・Social Outreach ・Selectivity of university ・Social attention ・Community-based ・General activity ・Jealousness 30
  • 32. Next Steps 1. To find associations or rules between the five categories and ten aspects. 2. To clarify the methodology in order to refine the associations or rules by machine learning. 3. To specify the evaluation method of the above methodology. 31
  • 33. Future Work  Extend the analysis to other SNS such as Facebook or Blogs.  Twitter is difficult to specify the user profile. 32

Notes de l'éditeur

  1. Trinity College Dublin – Old Library 1592
  2. http://energise2-0.com/2014/04/02/ivory-tower-bucking-social-media/
  3. http://www.unseminary.com/4-strategies-for-silencing-rumor-mongers/