social web 2014: final presentations (part i)
DESCRIPTION
Final presentations by students in the Social Web Course at the VU University Amsterdam, 2014 (groups 1-15)TRANSCRIPT
Group 1
Features
a project by
tsw I group01
hardie I pinzi I piscopo
Concept
Target users
What> social profiles> user posts > user played music
Data set 1Facebook user
statuses and posts
Data set 2Last.fm listened
tracks
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
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
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
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
Group 2
The Social ThermometerThe Social Web - VU University AmsterdamGroup 2: Adnan Ramlawi, Sindre Berntsen, Yaron Yitzhak
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
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
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.
Progress - What we have so far...
Acknowledgements:
All: brainstorming, reportYaron: data retrievalSindre: data processingAdnan: data visualisationAdnan, Yaron: presentations
Group 3
Sleep@Broad Begoña Álvarez de la Cruz Aristeidis Routsis Giorgos Lilikakis
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
Goals
o Reduce the financial cost of exploration
o Motivate the traveler to explore new places
feeling safer
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
Our application : Sleep@Broad
Welcome page
Login
Our application : Sleep@Broad
Friends’ location
Our application : Sleep@Broad
Friend List
Our application : Sleep@Broad
Friends in a specific location
Questions ?
Group 4
@ Twitter username:
ENTER
Group 4: Hassan Ali Annemarie Collijn Julia Salomons
Hashtags Research tool
Twitter Followers World Map
Twitter Followers Locations Map
Hashtag Word Cloud
Interactive word cloud based on hashtags
Link to tweets with the clicked hashtag (#whereihandstand)
Work Division
Hassan Ali Writing of Report Annemarie Collijn Development of App Julia Salomons Development of app
Group 5
Travel Together
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
Achraf Belmokadem
Bernd Themann
Sheldon Pijpers
Group 5Motivation
Achraf Belmokadem
Bernd Themann
Sheldon Pijpers
Group 5Motivation
Achraf Belmokadem
Bernd Themann
Sheldon Pijpers
Group 5Approach
Magic
+
Travel Together Control Center
Building a community + reuse of existing data
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
Achraf Belmokadem
Bernd Themann
Sheldon Pijpers
Group 5Approach
Magic
+
Travel Together Control Center
Building a community + reuse of existing data
Working place
Opening hours
Achraf Belmokadem
Bernd Themann
Sheldon Pijpers
Group 5Approach
Magic
+
Travel Together Control Center
Building a community + reuse of existing data
Realtime Updates
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
Achraf Belmokadem
Bernd Themann
Sheldon Pijpers
Group 5Screenshots
Search-and
Displayoptions
Resultsection
Option to shareon Facebook
and Twitter
X-Ray Mode
Achraf Belmokadem
Bernd Themann
Sheldon Pijpers
Group 5Screenshots
Searchradius
Related Messages
Achraf Belmokadem
Bernd Themann
Sheldon Pijpers
Group 5ScreenshotsX-Ray Mode for easily finding matching routes
Achraf Belmokadem
Bernd Themann
Sheldon Pijpers
Group 5ScreenshotsAbility to contact friends
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
Thanks!
Group 6
Proofread PalGroup 6: Bob de Graaff, Justin Post and Melvin Roest
What is Proofread Pal?
The simplest and quickest way to have your documents proofread!
How does it work?
User Expertise
Matching algorithm● Similar domain knowledge● Similar personality profile● Similar “Proofread Pal” ranking
A match!
Let’s take a look
What’s next?● Queue times based on ranking!● Text mining for better document
classification!● Weighted evaluation!
● Dolphins!
Thanks for listening!
Are there any questionsnot regarding dolphins?
Group 7
#Social Web 2014
#Group 7
#Benjamin Timmermans
#Rens van Honschooten
#Harriëtte Smook
#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
#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
#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
#screencast
Group 8
#analyzing Twitter’s Trending Topics
The Social Web, 2014
Group 8: Ans de Nijs, Matthijs Rijken, Lia Sterkenburg
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.
Analysis of existing tools
• Twistori (sentiment keyword search) à
• We feel fine (feeling analysis) à
• I-logue (trending topic word cloud)
Data
• Twitter Tweets (100s - 1000s) • Text
• Timestamps
• Extract keywords
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
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
Group 9
Odd “like” out
Group 9
Lennert Gijsen, Mustafa Küçüksantürk & Ömer Ergül
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.
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.
Demo
Demo
Demo
Demo
Demo
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
Individual work- Explore possibilitiesOmer, Mustafa
- Retrieving and analysing Facebook dataLennert, Omer
- ProgrammingLennert, Mustafa
- TestingEveryone
Questions ?
Group 10
Rcmdr/UTV Timothy Dieduksman, Guangxue Cao, Adi Kalkan
Rcmdr/UTV, Group 10
IMake Problem: ● Irrelevant
recommendations ○ Annoyed viewers
● Goal: ○ Provide users
relevant recommendation
Data & Analysis
SCORE
Demonstration
Group 11
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
CARSIDEROR: Car Perception For (potential) buyers & car manufacturers
G11
CARSIDEROR: Car Perception For (potential) buyers & car manufacturers
G11
CARSIDEROR: Car Perception
Feature 1: Positive/negative/neutral classification (tweets)
For (potential) buyers & car manufacturers
G11 By Andreas Karadimas
CARSIDEROR: Car Perception For (potential) buyers & car manufacturers
G11
CARSIDEROR: Car Perception
Feature 2: Location-based analysis
For (potential) buyers & car manufacturers
G11 By Luxi Jiang
CARSIDEROR: Car Perception For (potential) buyers & car manufacturers
G11
CARSIDEROR: Car Perception
Feature 3: Positive/negative/neutral proportion analysis
For (potential) buyers & car manufacturers
G11 By Micky Chen
CARSIDEROR: Car Perception For (potential) buyers & car manufacturers
G11
Group 13
PoPlacesGroup 13:Thom Boekel, Rianne Nieland, Maiko Saan
popular places among your friends
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.
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)
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
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
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
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
Group 14
Predicting the local elections
with Twitterdata
GROUP 14
Mabel Lips
Marco Schreurs
Wouter van den Hoven
Data & Approach
• Our data
• Collection of tweets of political parties and prominent politicians
• Size of data: ~15.000
• Approach
• Sentiment analysis
• Normalisation
Purpose of WebApp
• Predict the outcome of the local elections
• People of Amsterdam interested in politics
• Unique:
• Using realtime Twitter data
• Normalisation
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
Individual work
• Wouter: Twitterdata retrieval
• Marco: Sentiment analysis of Twitter data
• Mabel: Algorithm sentiment analysis and normalization process
Group 15
Twitter Recommendation App
Group 15 - Niels, Dick & SarahMarch 2014
Goal
Discovering interesting Tweets, subjects and users.
System Overview
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.
Semantic Markup
● Allows for machine understanding● schema.org/{CreativeWork, Person}● Suggestion: schema.org/MicroBlogPost
Feature Sarah
● Discovering and extracting recurring terms (i.e. common subjects)
● Categorization and visualization of interesting and uninteresting Tweets
Feature Niels
Recommending Tweets
● Part of the larger system● Basis for more features
Questions or Feedback