SPREE

A Community-Based Information Exchange Network

Competence CenterInformation Retrieval and Machine Learning
ContactProf. Dr.-Ing. Sahin Albayrak
Founded by: Deutsche Telekom Laboratories
Website: www.ASKSPREE.de

 

The 'classical' internet provides information in the form of documents. Users searching for information can either directly access these documents or use search engines to identify the most relevant ones for a given query. However, in some cases instead of finding a document the user might want to find the right person to ask. This way the user benefits from the interactive communication process and the result quality is expected to be higher and much more personalized. Technologies such as blogs or discussion forums already try to cope with these problems but neither do they provide an automatic classification of given questions or the automatic identification of those users best capable of answering, nor do most of them offer means for real-time communication between users and experts.

The SPREE project provides an online portal offering the functionality of automatically identifying the best qualified users (experts) for a given query. Furthermore the system offers means such as chat or email for a direct communication between user and expert in order to maximize the result quality.

Goal

The main focus of the SPREE project is the implementation of an online portal for an efficient knowledge transfer between its users. Therefore the platform has to be capable of identifying the best qualified users for answering a given query in real time, and the quality of the algorithm doing the matching between query and experts will be of central importance. Moreover the portal will provide means - such as chat - allowing users and experts to directly communicate with each other.

Implementation

The prototype developed in the SPREE project provides a platform for efficient expert identification and inter-user communication. The architecture of the spree framework allows for expert identification in real time providing high quality matching results at the same time. To realize this goal a suitable ontology for classifying users and queries is implemented. A client-server communication based on AJAX technologies is used in order to cope with the platform's real-time requirements and to provide a dynamic user experience.