We have released a new version of our app recommender system. Install the latest version by scanning the QR code or downloading from Android Market.

Some screenshots

You can see the peaks around lunch and dinner time. So people seem to check-in when they are out for having a meal at places where they have a meal. Furthermore, you can now share apps on Facebook and Twitter — just connect your accounts. So if you find any interesting curves, we will be happy if you share them with us and your social networks.

Behind the scenery, we are experimenting with new recommender engines. For instance, knowledge of when apps are mostly used during course of the day will be used to improve recommendations. From your feedback we know that we can further improve on the recommender quality. If you have any comments or feature request, we will be happy to know about it.

Please keep going on giving us feedback! We really like to meet your requirements for a perfect app recommender. For the next release, we are planning to re-design the UI and provide some smaller features to round up the recommender system.

You can use this QR-tag to download the new version of appazaar.

Thank you also for all the great feedback that you sent us by mail! We really want to keep up with all of your feature requests. Some of them will already be available in the next release. For instance we are working on the integration of everything into full app instead of forcing you to use the large widget. We are also thinking about providing different form factors for the widget. What do you think?

appazaar is a recommender system for Android apps. It learns which applications are interesting for a user and recommends applications according the user’s personal taste. Therefore it tracks the application usage and compares it to other peoples interests in applications. Thereby appazaar is able to give personalized recommendations of apps.

Furthermore, appazaar is not only tailored to the user’s app taste, it is also location-aware. Android users are mobile people and often change their location. With their location they also change their activity, for instance from working at the office to chilling at the beach. appazaar uses that to optimize its recommendations! Surely you agree that you require apps for productivity at work and games and music apps for relaxing at the beach. 0:1 for Android and appazaar! Apple’s Genius fails in making this small but important distinction.

The more people are using appazaar and the more appazaar knows about their application usage, the better the recommendations will be. appazaar is currently in the fledgling stages but growing fast. So give it a try and use it for a while.

appazaar is available on the Android market and can be used without any registration or login right away. Just get it and receive personalized and location-aware recommendations for all those cool apps out there!

appazaar is a project of the Software Engineering Lab at Münster University of Applied Sciences, Germany. The research group is working on location- and context-aware mobile systems.

CaRR2011 :: IUI2011 Workshop on Context-awareness in Retrieval and Recommendation
Location: Palo Alto, California, USA
Date: February 13, 2011
Website: http://www.dai-labor.de/carr2011/

General Information
Context-aware information is widely available in various ways such as interaction patterns, location, devices, annotations, query suggestions and user profiles and is becoming more and more important for enhancing retrieval performance and recommendation results. At the moment, the main issue to cope with is not only recommending or retrieving the most relevant items and content, but defining them ad hoc. Further relevant issues are personalizing and adapting the information and the way it is displayed to the user’s current situation (device, location) and interests.
In this workshop we focus on the integration of context for retrieval and recommendation.
We recognize a general content context and a user-centric content context. A general content context is a common case defined by time, weather, location and many similar other aspects. A user-centric content context is given by the content of user profiles such as language, interests, devices used for interaction, etc.

Call for Papers
The aim of the CaRR Workshop is to invite the community to a discussion in which we will try to find new creative ways to handle context-awareness. Furthermore, the workshop aims at improving the exchange of ideas between different communities involved in research concerning, among other machine learning, information retrieval and recommendation.
The workshop is especially intended for researchers working on multidisciplinary tasks who want to discuss problems and synergies. We are interested in ideas about creative and collaborative approaches for context-aware retrieval and recommendation.

The participants are encouraged to address the following questions:

• Why is context-awareness in retrieval and recommendation necessary?
• Which benefits come from context-aware retrieval and recommendation systems?
• How do user interfaces handle context?
• In what ways can context improve HCI?
• How can we combine general- and user-centric context-aware technologies?
• How should context affect the way information is presented?

The topics of interest include, but are not limited to, the following aspects:

• Context-aware information retrieval
• Context-aware profiling, clustering and collaborative filtering
• Machine learning for context-aware information retrieval and ontology learning
• Ubiquitous and context-aware computing
• Use of context-aware technologies in UI/HCI
• Context-aware advertising
• Recommendations for mobile users
• Context-awareness in portable devices

Paper submissions and reviews will be handled electronically through the CaRR page in EasyChair (which will be made available at a later point in time).

Important dates

• Paper submission: November 1, 2010
• Notification: December 12, 2010
• Camera-ready submission: December 19, 2010
• Workshop: February 13, 2010

Organizers and Committees
General Chairs (carr2011@dai-lab.de)

• Ernesto William De Luca, DAI Lab/Technische Universität Berlin
• Alan Said, DAI Lab/Technische Universität Berlin
• Matthias Böhmer, Münster University of Applied Sciences
• Florian Michahelles, ETH Zurich

Industrial Chair

• Sahin Albayrak, DAI Lab/Technische Universität Berlin

Program Committee

• Sarabjot Singh Anand, University of Warwick, UK
• Gernot Bauer, Münster University of Applied Sciences, Germany
• Shlomo Berkovsky, CSIRO, Australia
• Toine Bogers, Royal School of Library Information Science, Denmark
• Gregor Broll, LMU/Docomo, Germany
• Li Chen, Hong Kong Baptist University, China
• Ed Chi, PARC, USA
• Marco Degemmis, University of Bari “Aldo Moro”, Italy
• Aldo Gangemi, Italian National Research Council, Italy
• Ido Guy, IBM, Israel
• Olaf Hartig, Humboldt-Universität zu Berlin, Germany
• Dietmar Jannach, TU-Dortmund, Germany
• Carsten Kessler, University of Münster, Germany
• Thomas Kirste, Universität Rostock, Germany
• Antonio Krüger, DFKI, Saarbrücken, Germany
• Michael Kruppa, DFKI, Berlin, Germany
• Neal Lathia, University College London, UK
• Ulf Leser, Humboldt-Universität zu Berlin, Germany
• Johannes Leveling, Dublin City University, Ireland
• Pasquale Lops, University of Bari “Aldo Moro”, Italy
• Bernd Ludwig, University of Erlangen-Nürnberg, Germany
• Stefan Mandl, University of Erlangen-Nürnberg, Germany
• Thomas Mandl, University of Hildesheim, Germany
• Marco Pennacchiotti, Yahoo!, USA
• Till Plumbaum, DAI Lab/Technische Universität Berlin, Germany
• Francesco Ricci, Free University of Bozen-Bolzano, Italy
• Christoph Schlieder, Universität  Bamberg, Germany
• Edmund Schuster, MIT, USA
• Bracha Shapira, Ben Gurion University, Israel
• Armando Stellato, University of Tor Vergata, Rome, Italy
• Jesse Vig, Universtity of Minnesota, USA
• Robert Wetzker, TU-Berlin, Germany
• Qiang Yang, Hong Kong University of Science and Technology, China

Abstract: Current technology development in mobile computing and upcoming application stores enable an easy development and distribution of mobile applications. This leads to an increasing number of available applications and to the user’s problem of content discovery. Recommender systems aim at guiding users to relevant items. Currently, recommender systems for mobile applications neglect that the usage of mobile devices is characterized by perpetual changes of a user’s context. In this paper, we give rise to the context-aware recommendation of mobile applications. We explore the design space of recommender systems for mobile applications and describe the different dimensions and techniques for capturing the users, the items, the contexts and the corresponding relevances. For proof of concept we present the prototype of a recommender system that combines the design options in a hitherto unexplored way.

You will find the approach described in the paper and some other ideas that came up and have been reported to us in the last weeks within the next version of appazaar. It will mainly improve our recommender system and fix some bugs of the Android app.

While you’ve been looking for new apps using the lastest version of appazaar, we baked a new version with a lot of improvements and integrated a lot of your feedback as well as our own ideas into it! And now, after a long time of testing, it is finally available in the Market

This is what the new mobile app looks like:

This are our changes in detail:

• “What are you just doing?”: Our recommendations are now tailored to your activity! Just answer the question and tell us something about your current activity to get the right apps.
• Tags for your activity: So far you had to insert free text to describe your activity. Now you can use tags to describe your current context more quickly. And in addition you can now connect appazaar with Facebook! The tags you insert into the widget are directly posted to your status on Facebook
• Blacklist: An app recommendation appears all the time and you don’t like it? Now you’re able to get rid of it by adding apps to a blacklist which can be edited within the settings.
• Scrolling: You are now able to scroll through our recommendations from page to page directly within the widget. We think, this is a good tradeoff between widget size and the number of recommendations. What do you think?
  
• Battery usage (GPS): Moritz did a really great job to improve the performance and battery usage. Nevertheless, for now we can not completely abandon the use of GPS positioning. Specially in areas with bad wireless/wifi coverage or insufficient accuracy appazaar falls back on gps positioning. There are already some more ideas in the pipeline to reduce this further and we’re confident to be able to minimize the usage of GPS further with the upcoming versions!

So just update appazaar or download it via the Market Store and let us know what you think about it

(If you experience some issues after updating, please try a clean reinstall before submitting a bugreport!)

In the meantime we have some great news: We will present appazaar at Pervasive 2010 – The Eighth International Conference on Pervasive Computing. We got our poster “Contextualizing Mobile Applications for Context-aware Recommendation” accepted for presentation and the reviews are very motivating! Here’s a short summary of the papers content:

Abstract: Current recommender systems for mobile applications neglect the very mobility of their users and their perpetually changing contexts. Although applications naturally serve for a special purpose, they cannot be addressed to a particular context of use. Hitherto, context information is not taken into account for the recommendation of mobile applications. In this paper we present work in progress on a platform that gives rise to context-awareness for mobile application recommendation. It records the users’ application usage and relates it to context information that is traced on the users’ devices. Thereby we can determine the context of use of the applications. We describe the conceptual design of a recommender system that exploits this information and suggests only contextual relevant applications to its users. A prototype implementation is presented.

If you are interested in all the techniques and algorithms running behind the software, you can meet us at Pervasive 2010 in Helsinki, Finnland. You’ll also find the paper and the poster on this website after the presentation at the conference. However, if you cannot make it to the conference, please drop us an e-mail for any feedback, question or suggestion.

Oh and by the way, the next release is coming soon, we are just in the phase of stabilizing the new features. And it’ll come with a lot of new features and improvements