Student Projects

#Travel: Search for topics shared among city locations

#Travel Landing Page

Title: Automatic detection of topics in the city and the associated locations
Duration: One semester (September – December 2014)
Responsible TA: Pearl Pu
Student Name: Renato Kempter
Goals: Design a novel way to recommend interesting places for visiting in the touristic city based on the feedback from social media.
Solution: Web application for exploring trending themes of city locations and finding a set of places to visit for each theme. The locations are extracted from the geo-localized photos of Instagram; and their themes are detected by topics of the associated hashtags.
Keywords: recommender systems, topic modeling, instagram, travel recommendation, system design

People often have a subject, a taste, a style or an interest that guides them to visit places they like. Nevertheless, traditional online travel guides are giving recommendations rather based on the categories of the places and their rankings. In this project, we suggest to use user-generated content to aggregate additional information about locations. Using geo-localized photos from Instagram and their associated hashtags, we develop a system that: a) Automatically clusters a set of instagrams with respect to existent city locations, b) Extracts the trending topics in the hashtags associated with the photos, and c) Generates sets of diverse locations that share the same topic. As topics are extracted directly from the user-generated content, they are more dynamic than predefined category- or tag-based descriptions of locations and reflect user interests and context of visiting those places. The example topics we were able to extract are “Christmas,Christmastree” and “design,vintage,deco”. Finally, we design a web application where users can browse the various topics and their corresponding locations in order to discover locations that suit their taste, style, or interest.

Resources: Demo website

Wine Exploration and Recommendation System


Title: Wine Exploration and Recommendation System
Duration: One semester (September – December 2014)
Responsible TA: Pearl Pu
Student Name: Cédric Rolland
Goals: Design a novel way to recommend and discover wines, which would not require prior knowledge of wine.
Solution: iPhone application for user-centric wine recommendation, exploration and shopping. It features the tailored quiz for taste learning in order to discover wines a user might like. It also includes knowledge quizzes for teaching users wine-related concepts and a reward system for motivating users buying more wines and continuing using the application.
Keywords: recommender systems, interface design, gamification, e-commerce, mobile application design

Wine recommendation is a default feature of multiple websites and applications selling wine. It usually asks the user to input their favorite bottles or give ratings to different wines, and then makes a recommendation based upon this information. However, it can be tedious for users, especially for those with little knowledge about wine. We wanted to design a new way of selling and presenting wine to customers, the way that would not require prior knowledge about wine and would be engaging for users. This resulted in the application called La Caveauté. It recommends wine to users based on the simple quiz about their taste preferences, such as for coffee, breakfast, juices, etc. The user answers to the multiple-choice questions, and the app adds the related tags to the user profile. The algorithm then recommends a wine based on those tags. In addition to the taste quiz and recommending wine, the application provides the full user experience for wine exploration, learning oenology and selecting the most appropriate wine for the moment. The design went through multiple iterations based on the collected user feedback.

Predicting Influence of Online Reviews with Emotion Extraction [Archived]

Duration: One semester (can be adapted to both bachelor and master students)
Goals: Improve our prediction capability of influence among reviews from e-Commerce websites, and our understanding of human behavior in this setting.
Responsible TA: Lionel Martin  and Pearl Pu
Keywords: emotion recognition, influence detection, prediction, social media analysis, natural language processing

Reviews keep playing an increasingly important role in the decision process of buying products and booking hotels. However, the large amount of available information can be confusing to users. A more succinct interface, gathering only the most helpful reviews, can reduce information processing time and save effort. To create such an interface in real time, we need reliable prediction algorithms to classify and predict new reviews which have not been voted yet but are potentially helpful. So far such helpfulness prediction algorithms have benefited from structural aspects, such as the length of review or its readability score. Since emotional words are at the heart of our written communication and are powerful to trigger listeners’ attention, we believe that they can serve as important parameters for predicting helpfulness of review texts. This is an excellent opportunity to develop a combined approach of Machine Learning and Natural Language Processing to improve the prediction of these influential reviews and provide a light interface to users.

The responsible student will:

  1. Familiarize with existing techniques in influence prediction and emotion extraction
  2. Discover and try the existing framework for prediction
  3. Develop new learning mechanisms to extract emotions from review texts
  4. Understand the features of interest in the prediction process
Related Skills: Programming skills (Python, Matlab or similar for prediction); Interest in Machine Learning, Natural Language Processing, and/or Text Mining; French or English mother tongue a plus

Persuasive technology in Group Lifestyle Recommender Systems [Archived]

Duration: One semester
Goals Persuasive technology aims to change people’s behavior or attitude through persuasion and social influence, but not coercion. Particularly, social influence has been identified as an effective component in motivating users’ behavior change in lifestyle. This project aims to develop a group lifestyle recommender system by applying persuasive technology based on a group recommender system called GroupFun.
Responsible TA: Yu Chen  and Pearl Pu
Keywords: Persuasive technology, social influence, behaviour change

The student will develop a group lifestyle recommender system based on a group music recommender system called GroupFun and conduct user studies to evaluate the system.

More concretely, the responsible student will perform the following tasks:

  • Qualitative research: including 1) conduct interview with real users to identify their goals, needs and requirement and 2) survey competitor products, relevant studies and identify novel approaches.
  • Prototype: Design and implement the lifestyle recommender using social influence based on qualitative research.
  • User study: Evaluate the system and persuasion technology with real users.
Related Skills: Java. Mobile app development experience  is a plus.

Wellness Sensing Using Wearable Sensors


Title: Wellness Sensing Using Wearable Sensors
Duration: One semester (February – June 2012)
Responsible TA: Dr. Zerrin Yumak
Student Name: Javier Martin De Valmaseda
Goals: Develop a stable platform for mobile sensor data collection, labeling and post visualization method.
Solution: Android mobile application for activity labelling and accelerometer data collection.
Keywords: mobile sensors, pervasive healthcare, time series analysis, ubiquitous computing, data collection

Activity recognition of every day activities can be used for many different purposes: preventive medicine, promotion of health-enhancing physical activities and a developing a healthier lifestyle. It has a high industrial interest and a high impact on society. In the same time wearable sensors are becoming less and less intrusive and more accurate. As well, mobile devices are becoming increasingly sophisticated and smartphones with accelerometer and other sensors are widely popular nowadays. In our study data have been collected by 8 users while performing normal daily activities along 2-3 days. They used two different types of sensors: BodyMedia and Affectiva together with an Android phone. We relied on the SAX method to process the data. Afterwards, it can be analyzed by machine learning algorithms to detect certain activity types. SAX is the first method for the symbolic representation of time series that allows dimensionality reduction and indexing with a lower-bounding distancemeasure. This symbolic approach allows a time series of length n to be reduced to a string length w (w < n).


Emotional Kineticons in Online Social Environment


Title: Emotional Kineticons in Online Social Environment
Duration: One semester (February – June 2012)
Responsible TA: Yu Chen
Student Name: Alfredo Cerezo Luna
Goals: Visualize and express emotions in online social environments.
Solution: Embed emotion in Facebook profile pictures.
Keywords: Interface Design, Emotion Visualization
Abstract: We started by defining a library of 9 kineticons according to music related emotions, such as: transcendence, joyful, wonder, tenderness, nostalgia, pacefulness, energy, sadness and tension. We then implemented the kineticons in GroupFun, a group music recommender system that suggests a common playlist for users. Our evaluation was based on a live user study. Aiming at proving that our kineticons are well understood we showed to 15 users our design together with 3 words description of emotion and asked them to vote for the words that best describe each of the 9 kineticons. Additionally, we prepared a video of 9 emotions, each corresponding to a song. All 15 users watched the video and rated (from 1 to 5) the appropriateness of how the kineticons describe the emotions evoked by the song.

Tomorrow’s music player [Archived]


Title: Tomorrow’s music player
Duration: One Semester
Responsible TA: Nicolas Jones
Goals: The goal of this project is to design a new visual interface for an existing music recommender,
Solution: Extend the jlfm java library and create a music player (respecting the audioscrobbler protocol)
Keywords: audioscrobbler. interface, java,, library, middleware, mp3, protocol, streaming, visualisation

When the first music recommender systems appeared a few years ago, and Pandora set the trend as for what the interface should look like. Since then, many new recommenders and social music players have emerged, but little have presented an innovative interface, preferring to copy the industry’s current standard. This project aims at introducing some novelty in this process by removing some buttons which can be replaced by analysing a user’s behavioural pattern and inferring adequate actions from his implicit preferences. This reduction of visual items in the interface brings up some place for new elements, such as visual representations of social similarity amongst users, tag clouds, and more. The advantage of such a system is to use the recommendation power of an accepted and popular system, but providing an innovative interface, resolving many of the classic user interaction issues of dynamic music recommender systems Current Java libraries (from the Jlfm project) provide basic access to’s platform and allow to capture any stream of music. They can easily serve as a feed for a new interface. The interface could be written in Java, but could also be proposed as a web-page interacting with a server-instance of the existing Java libraries. The main steps of this project would be to first extend the communication means with creating a new music player (software or website) before working on additional features.

Required Skills
  • Good software engeneering skills (java or scala and possibly xhtml/css)
  • Basic HCI knowledge
  • Creativity and interest in music

iTunes automatic music classifier & scribbler [Archived]


Title: iTunes automatic music classifier & scribbler
Duration: One Semester
Responsible TA: Nicolas Jones
Goals: Classify music (and, possibly, recommend better music or generate automatic playlists)
Keywords: iTunes, preference elicitation

iTunes already incorporates a rating mechanisms, a genre classification, a playlists categorisation, and a play-count log. Unfortunately, this information is very rarely used by iTunes to represent data in a semi-automatic way. Furthermore, a majority of users don’t use these at all, and the small subset of those who do spend a lot of time with it. We propose to write a plugin who will rely on the users’ implicit preferences (behaviour) to rate the songs, classify them by similarity in automated playlists, and possibly creating an improved online musical profile on sites like

Project Results:
  • automatic rating mechanisms
  • automatic playlists
  • implementation of audioscrobbler protocol for submitting to online profile (
Required Skills
  • Good programming skills
  • Previous experience with iTunes plugins is a plus

Music Recommendation Database [Archived]


Title: Music Recommendation Database
Duration: One Semester
Responsible TA: Nicolas Jones
Goals: Creating a music recommender system. Setup a music database  as a first step.
Keywords: data collection, recommender systems

Recommender systems (RS) have started becoming popular to help users overcome the information overload problems on internet. Today’s trends of Web 2.0 and the emergence of social interactions, where content is created and shared by users, have lead to new contexts where RS are used such as music. The goal of the project is create a music database, usable for a future recommender system. The first challenge will be to organise and classify a comprehensive collection of music files (+10000 songs), leading to the second challenge ofcompleting the meta-data of each track, such as artist, track, album, etc. (through automated querying of the Gracenote database, or other) leading to the establishement of a rich and complete music database. The developpment should include the interface for listening and importing new songs. Finally, if time permits, the project will include the setting up of a basic music recommender. Based on the remaining time, the project can be extended such as to for example include data mining goals for add taging values to the songs. Many music websites provide web services for consulting tags related to tracks, and this could be used to create a second level abstraction, an ontology, for enhancing music recommendations.

Project Results:
  • Erection of collection of music files
  • Mapping from a music metadata database
  • Song recognition and assimilation of metadata
  • Importation interface
  • Software architecture for classifying files
Required Skills
  • Data parsing (java, scala or other)
  • Database manipulation (php/mysql)
  • Good Software engeneering skils

E-Commerce Shopping System for Mobile Viewers [Archived]


Title: E-Commerce Shopping System for Mobile Viewers
Duration: One Semester
Responsible TA: Jiyong Zhang
Goals: Design and implement a prototype e-commerce shopping website for mobile users.
Keywords: e-commerce, interaction design, plugin development

Over the past few years there has been an exponential growth both in the number of mobile users. Mobile internet enables users to access online information from mobile devices. An upcoming trend for mobile users would be to buy products directly through their mobiles from anywhere, at anytime.

In this project we intend to build or adapt a shopping website for mobile users. The system can be developed based on some existing open source shopping systems such as osCommerce ( We need to design a module so that the interface can be outputted adequately on mobile devices. This can be done by detecting the connecting device and modifying the stylesheets accordingly, or can also be based on the Wireless Application Protocol (WAP) and creation of wml pages. (The WAP is the world standard for the presentation and delivery of wireless information and telephony services on mobile phones and other wireless terminals, but more and more phones just integrate a light-version web browser). The challenge would be to design interfaces that can be conveniently used by mobile users, and to provide as a plugin/module for an existing and popular shopping system.

Project Results:
  • Implementation of a prototype mobile shopping system;
  • Usability issues of the mobile shopping system;
  • Publication of a plugin
  • Results analysis and report.
Required Skills
  • Previous experience of website development
  • CSS / PHP / Mysql
  • Development experience with CMS systems is welcome (optional)