Has it occurred to you that you want to watch movie and Netflix is providing the same set of movies based on your previous history? what if we are in a different mood or different mindset and want to watch something different, how good these systems are in those situations. May be thses are not good for those who want to watch diverse range of movies.
No, they are biased. And a biased system will be with aim of fulfilling the business goal by enhancing the TRPP of particular show, and would be of less use to the customer. I always avoid and recommendations on such issues.
There are several approaches that can be used to enable not being just stuck in a bubble of similar contents. You can find proposals that try to maximise serendipity, surprise, etc.
What you mention is a real problematic issue. We have recently developed a new generation recommender system that tries to break the filter-bubble effect by exploiting a process of creative (more serendipity-based) recommendation. The system has been tested on the RAIPlay platform and will be presented at the ECAI 2020 conference. If you are interested you can read more here: http://ecai2020.eu/papers/484_paper.pdf
Dear Sandhya,
Many models are indeed biased and you often get the same set recommendations over and over again due to your browse history in those systems. For example, consider that from September till May you watch horror movies, while from April till September, you watch comedies. Obviously, there is a change in your preferences but most models can't understand this evolution. Only a few research has been conducted in the literature related to this phenomenon that is known as "preference/temporal dynamics". It seems that in most online services this feature is not supported yet.
It's a good reflection. It's a research issue, we can take into account the current context (mood, season, weather,...) to improve the results of the recommendation.
- Badges
- Science topic
- Similar topics
- Linguistics
- Composition Studies
- Writing