When Amazon recommends a product, it is clearly not a coincidence. What their "collaborative filtering" recommendation system does is to retarget a visitor with what he or she has bought in the past, which items they have put into their shopping cart, and what other similar customers have recommended, viewed or purchased.
HMTL5 Word Cloud generates tag clouds by analyzing the most frequently used terms and phrases in Wikipedia articles, uploaded files, RSS feeds, and social media profiles (Facebook, Twitter, and Google+).
http://socialmediaslant.com/html5-word-cloud/
eMarketer predicts that by 2019, 65% of the global population will be using messaging apps. With so many messaging apps now supporting chatbots, it's not surprising that the global chatbot market is expected to grow exponentially between 2016 and 2023 (source: Credence Research).
Zoosk is an app that learns as you click in order to pair you with singles with whom you’re likely to discover mutual attraction. Zoosk’s Behavioral Matchmaking™ technology is constantly learning from the actions of all members in order to deliver better matches.
This mobile app is a social news aggregator that has recommendation engine and adaptive representation features based on your interests (in user profile). It collects implicit feedback from user interaction with the app and integrated this information o user profile.
Stackoverflow is a social Q&A website. It recommends questions to users who are interesting in the topics of the question based on the tags in user profile.
This article is related to user privacy. Users' trajectory is an important information as an input in location recommendation systems. However, because it is a sensitive data, it should be protected w.r.t user privacy.
T. Niebler, M. Becker, D. Zoller, S. Doerfel, und A. Hotho. Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, New York, NY, USA, ACM, (2016)