In recent lectures, we gained very useful knowledge about recommender systems, including fundamental knowledge, identifying the differences and similarities between different recommender systems, predicting ratings, how to evaluate recommender systems, etc.
First, we have reached a consensus that recommender systems are very useful and important in our daily life, since we make decisions every day, and we usually need the comments and feedback from others to help us make choices. This is also the reflection of human’s social attributes.
Since the user demands appeared, the recommender systems also appeared, like Facebook, Twitter, Amazon, Weibo, etc. Each recommender systems have their own design and more or less different from others. Let’s use Facebook and Twitter as an example.
The most direct and can be found immediately difference between Facebook and Twitter, in my opinion, is that they have different connection rules of users. Facebook requires the connections must me mutual, while twitter don’t.
In Facebook, users can share pictures, links, likes, and other things, while twitter can share them in a limited words.
Most important, twitter focuses on instant information, people can get the hot event at the first time in Twitter. Facebook mainly meet the demand of user’s daily life.
However, the two systems have the same goal, to help users communicate easily and widely. We can get more information in the below graph.
Thank you for sharing your ideas on recommender systems, recommender system is very common now on websites, but I hate it, it uses cookies to realize the recommending, I am kind of feeling losing my privacy, at the same time, whenever I do something, it will provide many recommendations, disrupting me, very annoying, although recommender system is a good technology, I don't like it.
回复删除The blog is very impressive since Xue has presented her findings in the difference between the twitter and Facebook,and the difference may because that people are likely to communicate in different ways.Like weibo and weixin in mainland,in weibo,people can only share few words because there remains a word number limitation.On the contrary,the blog which is very hot few years ago has no longer been hot,I believe that most people are too busy to read long articles nowadays and also the blog which is hot few years ago presents no focus.People prefer to absorb information in a faster way which is also a reason why the blog is no longer popular
回复删除Thanks for your sharing! In SNS, an efficient recommender system can really help us find new friends, or even friends that are lost connection for many year! :D
回复删除hi baixue, I scan your blog, and think your idea is quite deep and understandable and I believe through different views towards the same knowledge point, it must help to understand it more insightful, even though there maybe is not innovation of idea.
回复删除I like the topic. Also I read some interesting materials about Amazon's recommendation system. Judging by Amazon’s success, the recommendation system works. The company reported a 29% sales increase to $12.83 billion during its second fiscal quarter, up from $9.9 billion during the same time last year. A lot of that growth arguably has to do with the way Amazon has integrated recommendations into nearly every part of the purchasing process from product discovery to checkout. The company remains tight-lipped about how effective recommendations are.
回复删除