social web 2014: final presentations (part ii)

109

Upload: lora-aroyo

Post on 29-Nov-2014

1.947 views

Category:

Technology


2 download

DESCRIPTION

Final presentations by students in the Social Web Course at the VU University Amsterdam, 2014 (groups 16-23)

TRANSCRIPT

Page 1: Social Web 2014: Final Presentations (Part II)
Page 2: Social Web 2014: Final Presentations (Part II)

Group 16

Page 3: Social Web 2014: Final Presentations (Part II)

The Reincarnation App

Filip Ilievski Sylvia van SchieWouter Stuifmeel

The Reincarnation App • A social web application to let you see who you were in previous lives • The Social Web • March 20th, 2014, VU University Amsterdam

GROUP

16

Page 4: Social Web 2014: Final Presentations (Part II)

Introduction / ApproachTARGET Users of Facebook

GOAL Find the reincarnation chain of the user (all predecessors)

METHOD We hook up the user's date of birth to a person who deceased around the same date.

(margin up to three weeks)

VALUE The app is unique for it links data from Facebook to DBpedia and shows info about deceased people

It furthermore has a high entertainment value

The Reincarnation App • A social web application to let you see who you were in previous lives • The Social Web • March 20th, 2014, VU University Amsterdam

Page 5: Social Web 2014: Final Presentations (Part II)

Data flow

The Reincarnation App • A social web application to let you see who you were in previous lives • The Social Web • March 20th, 2014, VU University Amsterdam

Page 6: Social Web 2014: Final Presentations (Part II)

Data clustering

The Reincarnation App • A social web application to let you see who you were in previous lives • The Social Web • March 20th, 2014, VU University Amsterdam

Clustering is based on the 8 results we received whenentering the initial birth date of 20 March 2007.

Page 7: Social Web 2014: Final Presentations (Part II)

User interface

The Reincarnation App • A social web application to let you see who you were in previous lives • The Social Web • March 20th, 2014, VU University Amsterdam

Page 8: Social Web 2014: Final Presentations (Part II)

Group 19

Page 9: Social Web 2014: Final Presentations (Part II)

Social Web - Facebook Activity Checker

Thomas Berger, Kristoffer Lie Braathen, Timo Nijhof

Vrije Universiteit Amsterdam

March 20th, 2014

Page 10: Social Web 2014: Final Presentations (Part II)

What?How?Who?

What does it look like?

1 What?

2 How?

3 Who?

4 What does it look like?

Thomas Berger, Kristoffer Lie Braathen, Timo Nijhof Social Web - Facebook Activity Checker

Page 11: Social Web 2014: Final Presentations (Part II)

What?How?Who?

What does it look like?

Aim of the application

The overall goal is to explore when (ie: which days? what time?)users are the most active on Facebook.

Thomas Berger, Kristoffer Lie Braathen, Timo Nijhof Social Web - Facebook Activity Checker

Page 12: Social Web 2014: Final Presentations (Part II)

What?How?Who?

What does it look like?

Data mining

Pyhon script using Python SDK for Facebook;

Getting friends statuses and likes;

Categorize them, sum up all likes and statuses within acategory;

For the last week, sum up friends activities for each day.

Thomas Berger, Kristoffer Lie Braathen, Timo Nijhof Social Web - Facebook Activity Checker

Page 13: Social Web 2014: Final Presentations (Part II)

What?How?Who?

What does it look like?

Individual work

Thomas: Python code, documentation;

Timo: Charts, design of app, data integration anddocumentation;

Kristoffer: Charts, design of app, data integration anddocumentation.

Thomas Berger, Kristoffer Lie Braathen, Timo Nijhof Social Web - Facebook Activity Checker

Page 14: Social Web 2014: Final Presentations (Part II)

What?How?Who?

What does it look like?

Thomas Berger, Kristoffer Lie Braathen, Timo Nijhof Social Web - Facebook Activity Checker

Page 15: Social Web 2014: Final Presentations (Part II)

What?How?Who?

What does it look like?

Thomas Berger, Kristoffer Lie Braathen, Timo Nijhof Social Web - Facebook Activity Checker

Page 16: Social Web 2014: Final Presentations (Part II)

What?How?Who?

What does it look like?

Thomas Berger, Kristoffer Lie Braathen, Timo Nijhof Social Web - Facebook Activity Checker

Page 17: Social Web 2014: Final Presentations (Part II)

What?How?Who?

What does it look like?

Thomas Berger, Kristoffer Lie Braathen, Timo Nijhof Social Web - Facebook Activity Checker

Page 18: Social Web 2014: Final Presentations (Part II)

What?How?Who?

What does it look like?

Thomas Berger, Kristoffer Lie Braathen, Timo Nijhof Social Web - Facebook Activity Checker

Page 19: Social Web 2014: Final Presentations (Part II)

Group 21

Page 20: Social Web 2014: Final Presentations (Part II)

Concertify

Group 21

Bart Eijk, Theano Kotisi, Timur Carpeev

Page 21: Social Web 2014: Final Presentations (Part II)

Structured data

Visualizations

Page 22: Social Web 2014: Final Presentations (Part II)

Feature I: Clustering genres

blues-rock > blues & rock

viking metal > metal

synthpop > electronic & pop

Use pre-determined general tags blues, classical, country, dance, electronic, folk, hip-hop, indie, jazz, latin, metal, musicals, pop, reggae, rnb, rock

Page 23: Social Web 2014: Final Presentations (Part II)

Feature II: Clustering venues

Classification: most occurring word (genre)

Bag of Words model based on clustered tags

{'blues':  0.0,  'classical':  0.0,  'country':  25.476190476190474,  'dance':  7.1428571428571423,  'electronic':  7.1428571428571423,  'folk':  25.476190476190474,  'hip-­‐hop':  0.0,  'indie':  2.8571428571428572  ...  

Page 24: Social Web 2014: Final Presentations (Part II)

Feature III: Filtering & Visualizing of venues

| JSON data

| venue name

| latitude, longitude

| genre classification

| genre vector

Page 25: Social Web 2014: Final Presentations (Part II)
Page 26: Social Web 2014: Final Presentations (Part II)
Page 27: Social Web 2014: Final Presentations (Part II)
Page 28: Social Web 2014: Final Presentations (Part II)
Page 29: Social Web 2014: Final Presentations (Part II)
Page 30: Social Web 2014: Final Presentations (Part II)
Page 31: Social Web 2014: Final Presentations (Part II)

|  Limitations

{  Cold Start Problem/Popularity bias, ad hoc annotation behavior, weak labeling

{  Non-agreement on taxonomies

{  Ill-defined genre labels

{  Scalability of genre taxonomies

|  Scope

{  From taxonomies to folksonomies?

Page 32: Social Web 2014: Final Presentations (Part II)

|  Evaluation

{  User Qualitative Evaluation of the Application

|  Future Work / Developments

{  Hierarchical Classification

{  Alternative Autotagging Models

{  Combining data sources: hybrid context - content systems for

music classification & recommendation

Page 33: Social Web 2014: Final Presentations (Part II)

Group 22

Page 34: Social Web 2014: Final Presentations (Part II)

Exploiting Twitter data for the automatic annotation of Dutch

Public TV ProgrammingGroup 22

Guido van Bruggen, Jochem Havermans, Shailin Mohan & Frank Schurgers

The Social Web 2014, VU Amsterdam | Final Presentation Social Web App

Page 35: Social Web 2014: Final Presentations (Part II)

Goal:Helping the Netherlands Institute of

Sound and Vision to automatically annotate TV shows

Target user group:Clients of Sound and Vision

Page 36: Social Web 2014: Final Presentations (Part II)

Advantages:

● Use of existing data;

● inexpensive;

● instantaneous annotation;

● easy to implement;

● automatic detection of hot topics;

● less need for tedious human annotation.

much advantage

wow

such cheap

very automatic

amaze

so data

Page 37: Social Web 2014: Final Presentations (Part II)

Words per minute annotation

De Wereld Draait Door, 18-03-2014.Minute: 18:17.

Page 38: Social Web 2014: Final Presentations (Part II)

Pauw en Witteman, 18-03-2014. Viewers: 778.000. Total tweets: 2231.

Page 39: Social Web 2014: Final Presentations (Part II)

Additions

● Words per minute annotation

● fragmentation of episodes;

● access to tweet content of all tweets;

● normalizing tweet count with viewer

count;

Page 40: Social Web 2014: Final Presentations (Part II)

Group 23

Page 41: Social Web 2014: Final Presentations (Part II)

WhatsAround

“Be everywhere, anywhere!” Youssef Azriouil, Sara Chambel Pinheiro, Ana Rodrigues & Evangelia Marinaki

Page 42: Social Web 2014: Final Presentations (Part II)

"Footprint - Where I've Been" is a designed map app for adding notes and marking

places

“Flickr” capture, create, and share

photos

“Instagram” way to capture and share the

world's moments

“Worldcam” easy way of finding photos

from a specific venue

Page 43: Social Web 2014: Final Presentations (Part II)
Page 44: Social Web 2014: Final Presentations (Part II)

WhatsAround

FAST GLOBAL FUN

Way to share your life and travels with friends, family and community

Easiest way of finding out what's happening right now, anywhere and everywhere

Page 45: Social Web 2014: Final Presentations (Part II)

WhatsAround

Get user location

Serve up photos

Serve up place info

Send coordinates to

API (DataSets)

Page 46: Social Web 2014: Final Presentations (Part II)

WhatsAround

Customized search

Different perspectives on a place

Be part of history by documenting

Chronological sequence - Understand the evolution of the place

Page 47: Social Web 2014: Final Presentations (Part II)

Check your location in real time

No hashtags

Friends Vs Community

Clustering analysis

Page 48: Social Web 2014: Final Presentations (Part II)

Photographers

Travellers

Active users of social web apps

Page 49: Social Web 2014: Final Presentations (Part II)

SARA – Location Assessment

EVI – Instagram and Flickr API info retrieval

ANA – WikiLocation API connection

YOUSSEF – Mobile experience

Page 50: Social Web 2014: Final Presentations (Part II)
Page 51: Social Web 2014: Final Presentations (Part II)

Group 25

Page 52: Social Web 2014: Final Presentations (Part II)

Group 25Jesse Groen, Alessio Muis, Ragaselvi

Ratnasingam

Page 53: Social Web 2014: Final Presentations (Part II)

Our applicationFeatures of the applicationDataAnalysisIndividual features

Page 54: Social Web 2014: Final Presentations (Part II)

Where is it used for?Connect common hashtags to usersFun!Enrich tweets

Page 55: Social Web 2014: Final Presentations (Part II)
Page 56: Social Web 2014: Final Presentations (Part II)
Page 57: Social Web 2014: Final Presentations (Part II)
Page 58: Social Web 2014: Final Presentations (Part II)
Page 59: Social Web 2014: Final Presentations (Part II)
Page 60: Social Web 2014: Final Presentations (Part II)
Page 61: Social Web 2014: Final Presentations (Part II)

Clickable(Domain) RecommendationUser Dependent

Page 62: Social Web 2014: Final Presentations (Part II)

Twitter data:HashtagsTimes usedFollowers & following

Page 63: Social Web 2014: Final Presentations (Part II)

Cluster analysisTrends analysis

Page 64: Social Web 2014: Final Presentations (Part II)

Jesse: Common hashtags among friends

Alessio: User dependent - Your own content

Selvi: Recommendation among yourconnections

Page 65: Social Web 2014: Final Presentations (Part II)

AlessioSelviJesse@Group25

Thank you very much! #SW2014 #findyourhashtag #finalassignment

20 Mar via web

Favorite Retweet Reply

Page 66: Social Web 2014: Final Presentations (Part II)

Group 26

Page 67: Social Web 2014: Final Presentations (Part II)

GROUP 26-APP INTRODUCTION

• Goal: Find top popular places among my friends

• Function:

• 1. Filter different type of places

• 2. Find people from different countries like to go where?

• 3. Analyze our data

Page 68: Social Web 2014: Final Presentations (Part II)
Page 69: Social Web 2014: Final Presentations (Part II)

INDIVIDUAL WORK

• Annan Cheng: 1. Retrieve friends data from Facebook; 2.

Extract where friends have been from data; 3. Get friends

nationality through Google Geocoding API

• Jiahui Chen: Design the demo, realize the map, filter and

sequencing functions through Google map API, d3 and

JavaScript

• Ziyan Zong: Realize analyze data function by using different

visualization methods like histogram and pie chart, etc. Find

out meaningful and useful facts behind those data.

Page 70: Social Web 2014: Final Presentations (Part II)

Group 27

Page 71: Social Web 2014: Final Presentations (Part II)

Group 27Final assignment presentation

Page 72: Social Web 2014: Final Presentations (Part II)

Data● Twitter streaming API● VeryRelated API

Page 73: Social Web 2014: Final Presentations (Part II)

Approach● Search for query

○ Select most popular tweets○ Find most relevant terms○ Look for synonyms

● Select relevant terms○ Refine the query○ Update the results

Page 74: Social Web 2014: Final Presentations (Part II)

Mockup

Page 75: Social Web 2014: Final Presentations (Part II)

Added value● Interactive

○ Does suggestions● Intuitive

○ Clicking instead of typing● Interesting

○ 1 page overview

Page 76: Social Web 2014: Final Presentations (Part II)

Group 29

Page 77: Social Web 2014: Final Presentations (Part II)

Predicting attendance and outcome

of local elections - A web

applicationGroup 29:Remco DraijerRenee VaessenLily Martinez Ugaz

Page 78: Social Web 2014: Final Presentations (Part II)

Description & Goal

• A web application

▫ Local elections on March 19th in the Netherlands

• Predicting outcome and attendance

▫ Based on number of tweets

• Functions as an informative app

• Investigates correlation between tweets and:

▫ Outcome (number of seats in municipal council)

▫ Attendance (turnout)

Page 79: Social Web 2014: Final Presentations (Part II)

Approach

• Mining Twitter for location-based tweets

▫ Amsterdam, Den Haag, Rotterdam and Utrecht

• Nine parties selected

▫ All occur in four cities

• Extract tweets with party-name in text, user-name or user-description

▫ Preprocess data for duplicates and party-generated tweets

Page 80: Social Web 2014: Final Presentations (Part II)

Data

• Twitter streaming API

▫ Fetch tweets during 24 hours

• Interactive visualizations with d3.js

• Results: correlation between % of seats in council and % of tweets about parties

▫ For Amsterdam, Den Haag, Rotterdam, Utrecht

• Distribution of tweets over mining period

Page 81: Social Web 2014: Final Presentations (Part II)

Visualization

• http://www.remcodraijer.nl/socialweb/ass4/

Page 82: Social Web 2014: Final Presentations (Part II)

Group 30

Page 83: Social Web 2014: Final Presentations (Part II)

News TimelineThe Social Web 2014 - final assignment

Group 30

Page 84: Social Web 2014: Final Presentations (Part II)

Motivation & Purpose

• information

• easy, visual way of getting up to speed

• easier than reading a newspaper or an RSS reader

• like a more visual, web-based, Flipboard

Page 85: Social Web 2014: Final Presentations (Part II)

Data Sources

• media agencies around the world (list from Wikipedia)

• Twitter

• Bing image search

• Sentiment140

Page 86: Social Web 2014: Final Presentations (Part II)

Data Flow• get the trending stories from the news agencies

• find tweets about the stories

• perform sentiment analysis on the tweets

• get images (and videos) related to the story

• export via JSON API

Page 87: Social Web 2014: Final Presentations (Part II)

Data Flow• get the trending stories from the news agencies

• find tweets about the stories

• perform sentiment analysis on the tweets

• get images (and videos) related to the story

• export via JSON API

filtered by region and/or tag

Page 88: Social Web 2014: Final Presentations (Part II)

Display

• Web app

• Mobile friendly

• Responsive gallery

• See a prototype at http://www.mihneadb.net/news_timeline/

Page 89: Social Web 2014: Final Presentations (Part II)

Demo

Page 90: Social Web 2014: Final Presentations (Part II)

Demo

Page 91: Social Web 2014: Final Presentations (Part II)

Group 31

Page 92: Social Web 2014: Final Presentations (Part II)

The Social Web 2014 – Final assignment – G31: Jeroen Wever JWR970, Jeffrey Bruijntjes JBS257, Marije ten Brink MBK262

APPSPIRE!

What are his/her true aspirations?An entertaining way to discover dreams and desires of influential people… or your friends!

Page 93: Social Web 2014: Final Presentations (Part II)

The Social Web 2014 – Final assignment – G31: Jeroen Wever JWR970, Jeffrey Bruijntjes JBS257, Marije ten Brink MBK262

Goala. Discover aspirations of a person of your interestb. Compare your aspirations with othersc. Visualize aspirations in tag clouds or photo cloudsd. Find people who have specific aspirationse. Follow trends in our shared aspirations

Related work:Twitter Account Showdown

Page 94: Social Web 2014: Final Presentations (Part II)

The Social Web 2014 – Final assignment – G31: Jeroen Wever JWR970, Jeffrey Bruijntjes JBS257, Marije ten Brink MBK262

Approach: discover1. Retreive all tweets of user with Greptweet.com2. Clean up tweets, remove punctuation, stop words, links3. Use stemmer: matches verbs and nouns with same stem4. Use word list with aspirational verbs to extract tweets with aspirations5. Count occurrences of meaningful word

Other possible data sources: FB, blogs, Pinterest, Google+, ...

Page 95: Social Web 2014: Final Presentations (Part II)

The Social Web 2014 – Final assignment – G31: Jeroen Wever JWR970, Jeffrey Bruijntjes JBS257, Marije ten Brink MBK262

Approach: compareDetermine similarity between 2 users, based on amount of matching words: correlation

Page 96: Social Web 2014: Final Presentations (Part II)

The Social Web 2014 – Final assignment – G31: Jeroen Wever JWR970, Jeffrey Bruijntjes JBS257, Marije ten Brink MBK262

Approach: visualize

Tag cloud

Image cloud

Timeline

Page 97: Social Web 2014: Final Presentations (Part II)

Group 32

Page 98: Social Web 2014: Final Presentations (Part II)

Final Assignment: Group 32Francois Lelievre, Marek Janiszewski, Yahia El-Sherbini, David Marshall-Nagy

Page 99: Social Web 2014: Final Presentations (Part II)

Main Concept

■ An easy to use application to manage your SoundCloud collection and enhance the social experience with music

Page 100: Social Web 2014: Final Presentations (Part II)

Group Effort

■ Concept and Development: Marek and Francois

■ Concept and Testing: Yahia and David

Page 101: Social Web 2014: Final Presentations (Part II)

Technical Background

■ Based on the SoundCloud API■ In-browser interface

Page 102: Social Web 2014: Final Presentations (Part II)

Music Collection Overview

■ Check all my likes in one place■ Check all the tracks of a followed artist in

one place

Page 103: Social Web 2014: Final Presentations (Part II)
Page 104: Social Web 2014: Final Presentations (Part II)

Collection Management

■ Search for new songs■ Sort out and favorite your songs■ Follow artists

Page 105: Social Web 2014: Final Presentations (Part II)
Page 106: Social Web 2014: Final Presentations (Part II)
Page 107: Social Web 2014: Final Presentations (Part II)

Song Recommendation

■ Based on the selected genre and on the likes of followed people

■ Based on the recent likes of the followed artists

■ Visualized search results

Page 108: Social Web 2014: Final Presentations (Part II)
Page 109: Social Web 2014: Final Presentations (Part II)

Thank You for Your Attention!

Questions?