DRUGREC: We provide drug and treatment recommendations to medical doctors for their patients. We exploit similar patterns among patients of different clinical studies, and recommend them health interventions (such as to provide oxygen therapy) and drugs (e.g., Remdesivir) based on their symptoms’ or diseases’ similarity with patients of other similar clinical studies. Our approach can also provide explanations along with recommended treatments to assist doctors in understanding the reasons behind a suggested drug or health intervention.
MOOCRec: It provides to users recommendations of MOOCs (Massive Open Online Courses), so that they can acquire new skills they lack to get their dream job. The process is very simple: Users describe their studies and their dream job and the system recommends them related MOOCs/skills.
CheckInExpo: It utilizes the bluetooth technology to connect the “Smartphone” of visitors in Museums/Exhibitions/Shops with “Beacon” sensors to provide them advanced services such as real-time information about products or exhibits, recommendations, electronic favourite lists, etc..
rrecsys: It is an open source library in R to evaluate several recommendation algorithms (i.e., item-based CF, user-based, MF, etc.) using time-dependent and time-independent evaluation protocols.
MoviExplain:This is a movie recommender system that provides both accurate and justifiable movie recommendations.
GeoSocialRec:This is an online recommender system for Location-based Social Networks, where users can get explanations along with the recommendations of friends, locations and activities.
MetaRec: This is a recommender system based on graph-based algorithms which can run on a HIN (Heterogeneous Information Network) and all its sub-graphs, providing also meta path-based explanations.
JobRec: This is a job recommendation system for recommending academic position to researchers or professors. (in greek)
AdsRec: A news web site with advertisement recommendations (in greek)
SkillRec: An under construction website that recommends projects to researchers or professors for possible collaborations based on their skills and their research interests.
Adressa data set: It contains only the data of the 1st day (i.e.,1/1/2017) of the Adressa light version (1.4 GB). It accommodates 1356987 views/interactions on 6091 articles of 238124 unique users. This subset contains 8857 users, 9128 sessions, 2194 articles, timeview of the interaction, date, and time. We have found 18 article categories (e.g., 100sport,nyheter, ’pluss’, etc.) and 69 article sub-categories (e.g., nyheter—okonomi,nyheter—trondheim, ’pluss—okonomi’, ’pluss—magasin’, etc.) . You can download the processed data set from the following link