On gossip-based information dissemination in pervasive recommender systems

Abstract

Pervasive computing systems employ distributed and embedded devices in order to raise, communicate, and process data in an anytime-anywhere fashion. Certainly, its most prominent device is the smartphone due to its wide proliferation, growing computation power, and wireless networking capabilities. In this context, we revisit the implementation of digitalized word-of-mouth that suggests exchanging item preferences between smartphones offline and directly in immediate proximity. Collaboratively and decentrally collecting data in this way has two benefits. First, it allows to attach for instance location-sensitive context information in order to enrich collected item preferences. Second, model building does not require network connectivity. Despite the benefits, the approach naturally raises data privacy and data scarcity issues. In order to address both, we propose Propagate and Filter, a method that translates the traditional approach of finding similar peers and exchanging item preferences among each other from the field of decentralized to that of pervasive recommender systems. Additionally, we present preliminary results on a prototype mobile application that implements the proposed device-to-device information exchange. Average ad-hoc connection delays of 25.9 seconds and reliable connection success rates within 6 meters underpin the approach's technical feasibility.

Developing a Message Broadcasting System for Natural Disasters

“…Google Nearby Connections API is used in many different research studies. Eichinger et al (2019) proposed a new method for finding similar peers and exchanging items among them. The method was implemented by using this API.…”

MobRec: Mobile Platform for Decentralized Recommender Systems

“…Given a movie or TV show, other items are recommended. 51 Based on these APIs, we recommend new items to Alice based on Alice's own preferences and based on the preferences of similar people that Alice met. 50 https://developer.spotify.com/documentation/webapi/reference/browse/get-recommendations/, accessed 2020-07-20 51 https://developers.themoviedb.org/3/movies/get-movierecommendations and https://developers.themoviedb.org/3/tv/get-tvrecommendations, both accessed 2020-07-20…”

MobRec — Mobile Platform for Decentralized Recommender Systems

“…We see two possible solutions for this problem. First, we could let each user disseminate more than just his/her own item preferences/ratings and let him/her also send data from previous encounters [51] -this would also address the cold start problem new users will face. Another approach is to calculate the similarity of users in a different way, independent of the users' ratings.…”

“…For movie recommendations, we utilize the TMDB API. Given a movie or TV show, other items are recommended 51 . Based on these APIs, we recommend new items to Alice based on Alice's own preferences and based on the preferences of similar people that Alice met.…”

“…Fig. 11 shows how movie 50 https://developer.spotify.com/documentation/web-api/reference/ browse/get-recommendations/, accessed 2020-07-20 51 https://developers.themoviedb.org/3/movies/get-movierecommendations and https://developers.themoviedb.org/3/tv/get-tvrecommendations, both accessed 2020-07-20 recommendations are displayed. Each row indicates to the user why the recommendations are being displayed, some based on own preferences, some based on users previously met.…”