Social Web 2014: Final Presentations (Part I)

122

description

Final presentations by students in the Social Web Course at the VU University Amsterdam, 2014 (groups 1-15)

Transcript of Social Web 2014: Final Presentations (Part I)

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

Group 1

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

Features

a project by

tsw I group01

hardie I pinzi I piscopo

Concept

Target users

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

What> social profiles> user posts > user played music

Data set 1Facebook user

statuses and posts

Data set 2Last.fm listened

tracks

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

How> sentiment analysis> filtering> cross-correlation

Sentiment analysisColours encode

user’s mood

Listening prefsTracks played are shown

for each time slot

Playlist generationPlaylist generated

according to moods

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

Evaluation process> user study

Preliminary studiesUser profiling

Information needs

Low-fi prototypes

Hi-fi prototype

User evaluationOn a working prototype● Design evaluation● Information gains,

user relevance● Functionality

evaluation

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

Conclusions> critical aspects> future work

Moods detectionMinimum amount of data needed to reliably extract emotional patterns

Single sign onAt present, signing in each of the two

SNSs is needed

Moods detectionDatasets could be further expanded

and more elements analysed to detect users’ moods

Single sign onAuthentication through OpenId or

similar services should be implemented

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

Organisation> individual work

Graham HardieProgramming, data collection and data visualization

Viola PinziTheoretical analysis, visual design and data analysis

Alessandro PiscopoTheoretical analysis, visual design and data visualisation

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

Group 2

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

The Social ThermometerThe Social Web - VU University AmsterdamGroup 2: Adnan Ramlawi, Sindre Berntsen, Yaron Yitzhak

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

Introduction

● Weather issues:○ Too hot, too cold, too wet, et cetera○ Does the weather affect people’s mood?

● Is there a correlation between:○ Weather○ Twitter sentiment

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

The application:● Data used:

○ Tweets○ Weather data (temperature, precipitation, cloudiness)

● Analysis: ○ Classification of tweets○ Filtering

● Virtualization:○ Average sentiment of tweets vs. weather elements (per

day)○ ChartJS, Bootstrap

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

Code:

● How does the application work:○ Long, Lat retrieval via Google Maps API○ Weather data - World Weather Online (JSON).○ Tweets - Twitter API (filtered by long,lat,lang,date)

■ Tweets re-formatted (JSON)■ Tweets sent to Sentiment140 API

● Returned data is displayed in graphs using a ChartJS script.

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

Progress - What we have so far...

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

Acknowledgements:

All: brainstorming, reportYaron: data retrievalSindre: data processingAdnan: data visualisationAdnan, Yaron: presentations

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

Group 3

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

Sleep@Broad Begoña Álvarez de la Cruz Aristeidis Routsis Giorgos Lilikakis

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

Introduction & Context o Willingness to travel around the world

• Expensive

• Time to plan the trip (finding accommodation)

o Alternatives • Couch surfing (accommodate to a stranger’s house)

o Our application: • Leverage the hospitality of your friends

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

Goals

o Reduce the financial cost of exploration

o Motivate the traveler to explore new places

feeling safer

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

Approach & Method o Extract data from user’s Facebook account

• User’s friends

• User’s friends name

• User’s friends photo

• User’s friends current location

• Personal friends lists

o Visualization

• Google Maps API

• Map

• Markers

o Provide travel details

• Google flights

• Skyscanner API

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

Our application : Sleep@Broad

Welcome page

Login

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

Our application : Sleep@Broad

Friends’ location

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

Our application : Sleep@Broad

Friend List

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

Our application : Sleep@Broad

Friends in a specific location

Page 25: Social Web 2014: Final Presentations (Part I)

Questions ?

Page 26: Social Web 2014: Final Presentations (Part I)

Group 4

Page 27: Social Web 2014: Final Presentations (Part I)

@ Twitter username:

ENTER

Group 4: Hassan Ali Annemarie Collijn Julia Salomons

Hashtags Research tool

Page 28: Social Web 2014: Final Presentations (Part I)

Twitter Followers World Map

Page 29: Social Web 2014: Final Presentations (Part I)

Twitter Followers Locations Map

Page 30: Social Web 2014: Final Presentations (Part I)

Hashtag Word Cloud

Interactive word cloud based on hashtags

Link to tweets with the clicked hashtag (#whereihandstand)

Page 31: Social Web 2014: Final Presentations (Part I)

Work Division

Hassan Ali Writing of Report Annemarie Collijn Development of App Julia Salomons Development of app

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

Group 5

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

Travel Together

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

Achraf Belmokadem

Bernd Themann

Sheldon Pijpers

Group 5

Help user to find people with similar routes to their workplace

• Allows car pooling which saves fuel, reduces carbon dioxide emission and helps to

reduce traffic jams

• More social to ride with somebody else or use the car in case of bad weather

Achraf Belmokadem

Bernd Themann

Sheldon Pijpers

Group 5Purpose

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

Achraf Belmokadem

Bernd Themann

Sheldon Pijpers

Group 5Motivation

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

Achraf Belmokadem

Bernd Themann

Sheldon Pijpers

Group 5Motivation

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

Achraf Belmokadem

Bernd Themann

Sheldon Pijpers

Group 5Approach

Magic

+

Travel Together Control Center

Building a community + reuse of existing data

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

Achraf Belmokadem

Bernd Themann

Sheldon Pijpers

Group 5Approach

Magic

+

Travel Together Control Center

Building a community + reuse of existing data

Friendlist

Working and living place

Opening hours

Realtime updates

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

Achraf Belmokadem

Bernd Themann

Sheldon Pijpers

Group 5Approach

Magic

+

Travel Together Control Center

Building a community + reuse of existing data

Working place

Opening hours

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

Achraf Belmokadem

Bernd Themann

Sheldon Pijpers

Group 5Approach

Magic

+

Travel Together Control Center

Building a community + reuse of existing data

Realtime Updates

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

Achraf Belmokadem

Bernd Themann

Sheldon Pijpers

Group 5Approach

Magic

+

Travel Together Control Center

Building a community + reuse of existing data

Working and living place

Workinghours

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

Achraf Belmokadem

Bernd Themann

Sheldon Pijpers

Group 5Screenshots

Search-and

Displayoptions

Resultsection

Option to shareon Facebook

and Twitter

X-Ray Mode

Page 43: Social Web 2014: Final Presentations (Part I)

Achraf Belmokadem

Bernd Themann

Sheldon Pijpers

Group 5Screenshots

Searchradius

Related Messages

Page 44: Social Web 2014: Final Presentations (Part I)

Achraf Belmokadem

Bernd Themann

Sheldon Pijpers

Group 5ScreenshotsX-Ray Mode for easily finding matching routes

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

Achraf Belmokadem

Bernd Themann

Sheldon Pijpers

Group 5ScreenshotsAbility to contact friends

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

Achraf Belmokadem

Bernd Themann

Sheldon Pijpers

Group 5Evaluation

Burdon to join cummunity decreased

due to prefilled information and access

via Facebook account

Higher value for the user because even

not registered users are participating

„missuse“ of information

NLP techniques are really weak and

have a low accuracy

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

Thanks!

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

Group 6

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

Proofread PalGroup 6: Bob de Graaff, Justin Post and Melvin Roest

Page 50: Social Web 2014: Final Presentations (Part I)

What is Proofread Pal?

The simplest and quickest way to have your documents proofread!

Page 51: Social Web 2014: Final Presentations (Part I)

How does it work?

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

User Expertise

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

Matching algorithm● Similar domain knowledge● Similar personality profile● Similar “Proofread Pal” ranking

A match!

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

Let’s take a look

Page 55: Social Web 2014: Final Presentations (Part I)

What’s next?● Queue times based on ranking!● Text mining for better document

classification!● Weighted evaluation!

● Dolphins!

Page 56: Social Web 2014: Final Presentations (Part I)

Thanks for listening!

Are there any questionsnot regarding dolphins?

Page 57: Social Web 2014: Final Presentations (Part I)

Group 7

Page 58: Social Web 2014: Final Presentations (Part I)

#Social Web 2014

#Group 7

#Benjamin Timmermans

#Rens van Honschooten

#Harriëtte Smook

Page 59: Social Web 2014: Final Presentations (Part I)

#motivation

#useful

An easy way to find free things via Twitter

You don’t need to search for Twitter accounts about free things

You don’t need to have a Twitter account at all!

#unique

There are several Twitter accounts that tweet about freebies

Gratweet collects all new tweets about freebies for you.

Unique in The Netherlands

Page 60: Social Web 2014: Final Presentations (Part I)

#data

#what

Dutch tweets that contain the keyword ‘gratis’

Geographic coordinates of the tweets

Alternative: social web data from other resources such as Facebook

#pre-processing: filtering

Explicit tweets

Identical (re)tweets

Stopwords, meaningless words, personal pronounces

Timestamps, URLs

Page 61: Social Web 2014: Final Presentations (Part I)

#approach

#algorithms

Assign specific weights to words surrounding the keyword ‘gratis’

#backend

Cache tweets using Twitter API and Tweet.JS

#frontend

Visualizations made with D3.JS, Jquery, CSS, HTML

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

#screencast

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

Group 8

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

#analyzing Twitter’s Trending Topics

The Social Web, 2014

Group 8: Ans de Nijs, Matthijs Rijken, Lia Sterkenburg

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

Why this solution?

Our goal: Inform people on specific topics and how they developed over time.

•  People may not know what trending – or certain other – topics are about on Twitter.

Our solution: Visualization of trending topics as word clouds combined with insight on the explosion of tweets over time with sentiment analysis if the tweets are about good or bad news.

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

Analysis of existing tools

•  Twistori (sentiment keyword search) à

•  We feel fine (feeling analysis) à

•  I-logue (trending topic word cloud)

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

Data

•  Twitter Tweets (100s - 1000s) •  Text

•  Timestamps

•  Extract keywords

Page 68: Social Web 2014: Final Presentations (Part I)

Approach

1.  Use Twitter API •  GET search/tweets (Matthijs)

2.  Use Python packages •  Textblob (sentiment analysis - Ans)

•  Visualize sentiments of tweets over time in a cloud

•  Pytagcloud (word cloud visualization - Lia) •  Extract tags based on word frequencies

•  Important words are displayed larger

Page 69: Social Web 2014: Final Presentations (Part I)

Smart part

•  Filter out ‘meaningless’ words (e.g. ‘of ’, ‘that’) and process the ones that really matter •  Provide a condensed view of a trending topic in a word cloud.

•  Sentiment over time: shows changing opinions

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

Group 9

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

Odd “like” out

Group 9

Lennert Gijsen, Mustafa Küçüksantürk & Ömer Ergül

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

Our application● Odd one out game using “likes” from Facebook.

● Retrieve small list of likes for a selection of Facebook friend.

● Random pages(potential likes) are added to each list.

● Player has to pick the odd one(s) out.

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

Our application● Type: - Entertainment

- Raise awareness to other possible likes.- Give insight to what friends like in an interactive and fun way.

● Scoping: - Only usable with a Facebook account.- Facebook users who’s friends have enough likes.

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

Demo

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

Demo

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

Demo

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

Demo

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

Demo

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

Evaluation / Improvements● Measurables: - Amount of users / games played per day

- Variations in users per day- Users’ scores

● Future work: - Clustering for better matching of “likes”○ Creates more variety in difficulty

- Add scores○ Percentage correct on daily basis○ Leaderboards, shared between friends○ Makes users come back

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

Individual work- Explore possibilitiesOmer, Mustafa

- Retrieving and analysing Facebook dataLennert, Omer

- ProgrammingLennert, Mustafa

- TestingEveryone

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

Questions ?

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

Group 10

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

Rcmdr/UTV Timothy Dieduksman, Guangxue Cao, Adi Kalkan

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

Rcmdr/UTV, Group 10

IMake Problem: ●  Irrelevant

recommendations ○  Annoyed viewers

●  Goal: ○  Provide users

relevant recommendation

Page 85: Social Web 2014: Final Presentations (Part I)
Page 86: Social Web 2014: Final Presentations (Part I)

Data & Analysis

SCORE

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

Demonstration

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

Group 11

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

CARSIDEROR: Car Perception

Public opinions on car brands

Twitter data: pre-assigned domain-specific #hashtags

Retrieve tweets

Sentiment analysis

Distribute results - Geographically

For (potential) buyers & car manufacturers

G11

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

CARSIDEROR: Car Perception For (potential) buyers & car manufacturers

G11

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

CARSIDEROR: Car Perception For (potential) buyers & car manufacturers

G11

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

CARSIDEROR: Car Perception

Feature 1: Positive/negative/neutral classification (tweets)

For (potential) buyers & car manufacturers

G11 By Andreas Karadimas

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

CARSIDEROR: Car Perception For (potential) buyers & car manufacturers

G11

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

CARSIDEROR: Car Perception

Feature 2: Location-based analysis

For (potential) buyers & car manufacturers

G11 By Luxi Jiang

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

CARSIDEROR: Car Perception For (potential) buyers & car manufacturers

G11

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

CARSIDEROR: Car Perception

Feature 3: Positive/negative/neutral proportion analysis

For (potential) buyers & car manufacturers

G11 By Micky Chen

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

CARSIDEROR: Car Perception For (potential) buyers & car manufacturers

G11

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

Group 13

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

PoPlacesGroup 13:Thom Boekel, Rianne Nieland, Maiko Saan

popular places among your friends

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

Goal & Added value

Group 13: Thom Boekel, Rianne Nieland, Maiko Saan

Goal:

Helps you to find places to go to based on popular places among your friends.

Added value:

Information of friends might be more interesting to you than reviews available on the internet.

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

Data

Group 13: Thom Boekel, Rianne Nieland, Maiko Saan

Data source:

Facebook locations of friends

Wikipedia location information, future work

Size of data:

Information of all your friends, in our case: 140 friends (1819 locations) and 215 friends (2517 locations)

Type of data:

JSON files containing friends and locations (latitudes and longitudes)

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

Approach

Data collectionGather friend

locations from Facebook

ProcessCategorize data on year

Filter out locations without latitude and

longitude

VisualizationHeatmap with markers Heatmap → number of

friends Markers → all locations

Group 13: Thom Boekel, Rianne Nieland, Maiko Saan

Page 103: Social Web 2014: Final Presentations (Part I)

Visualization (1/2)

Group 13: Thom Boekel, Rianne Nieland, Maiko Saan

Visualization type:Google heatmap with location markers

Visualization of places: Locations marked with markers

Popularity of locations indicated with colors andradius

Page 104: Social Web 2014: Final Presentations (Part I)

Visualization (2/2)

Group 13: Thom Boekel, Rianne Nieland, Maiko Saan

Options:

Filter locations by year

Heatmap options (e.g. radius)

Infobox with:

● information about the location provided by Wikipedia

● friend visits per year

Page 105: Social Web 2014: Final Presentations (Part I)

Critical reflection

Pro’s:

● Filter on year● Indication of popularity of a

location (heatmap)● Able to perform pattern

analysis, e.g. Ziggodome (number of visits increases every year)

Con’s:

● Only locations your friends have checked in or were tagged

● Cannot see the names of your friends

● Only information for locations available on Wikipedia

Page 106: Social Web 2014: Final Presentations (Part I)

Group 14

Page 107: Social Web 2014: Final Presentations (Part I)

Predicting the local elections

with Twitterdata

GROUP 14

Mabel Lips

Marco Schreurs

Wouter van den Hoven

Page 108: Social Web 2014: Final Presentations (Part I)

Data & Approach

• Our data

• Collection of tweets of political parties and prominent politicians

• Size of data: ~15.000

• Approach

• Sentiment analysis

• Normalisation

Page 109: Social Web 2014: Final Presentations (Part I)

Purpose of WebApp

• Predict the outcome of the local elections

• People of Amsterdam interested in politics

• Unique:

• Using realtime Twitter data

• Normalisation

Page 110: Social Web 2014: Final Presentations (Part I)

Algorithms

• Sentiment analysis

• Pattern: python package with functionality for sentiment analysis

• SentiWordNet: Dutch sentiment lexicon (De Smedt and Daelemans, 2012)

Source image: http://jmlr.org/papers/volume13/desmedt12a/desmedt12a.pdf

Page 111: Social Web 2014: Final Presentations (Part I)

Individual work

• Wouter: Twitterdata retrieval

• Marco: Sentiment analysis of Twitter data

• Mabel: Algorithm sentiment analysis and normalization process

Page 112: Social Web 2014: Final Presentations (Part I)

Group 15

Page 113: Social Web 2014: Final Presentations (Part I)

Twitter Recommendation App

Group 15 - Niels, Dick & SarahMarch 2014

Page 114: Social Web 2014: Final Presentations (Part I)

Goal

Discovering interesting Tweets, subjects and users.

Page 115: Social Web 2014: Final Presentations (Part I)

System Overview

Page 116: Social Web 2014: Final Presentations (Part I)
Page 118: Social Web 2014: Final Presentations (Part I)

General Features

• Memory-based collaborative filtering.• Naive Bayes classifier to train on user’s timeline.• Linear discriminant analysis: interesting vs. uninteresting.• Continuous loop: retrieve Tweets and let user rate.

Page 119: Social Web 2014: Final Presentations (Part I)

Semantic Markup

● Allows for machine understanding● schema.org/{CreativeWork, Person}● Suggestion: schema.org/MicroBlogPost

Page 120: Social Web 2014: Final Presentations (Part I)

Feature Sarah

● Discovering and extracting recurring terms (i.e. common subjects)

● Categorization and visualization of interesting and uninteresting Tweets

Page 121: Social Web 2014: Final Presentations (Part I)

Feature Niels

Recommending Tweets

● Part of the larger system● Basis for more features

Page 122: Social Web 2014: Final Presentations (Part I)

Questions or Feedback