Developing a Framework for Recommending TV Shows
Developing a Framework for Recommending TV Shows
复制标题
开发电视节目推荐框架
DOI：
10.1109/iciev.2017.8338560
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Yasuhiko Morimoto
中科院分区：
文献类型：
--
作者：
Chondrima Chowdhury;Mohammad Shamsul Arefin;Yasuhiko Morimoto
推荐系统在过去的十年中得到了积极的研究，并在研究和工业界都得到了广泛的关注。因此，现在我们可以找到关于新闻，书籍，电影，产品，位置等的推荐。然而，电视节目的推荐技术虽然重要，但却没有得到积极的研究。这是因为开发电视节目推荐系统需要考虑两个重要问题。首先，电视节目只在一段时间内可用。第二，用户不能同时观看两个不同的节目。虽然有一些电视节目推荐系统，但大多数推荐系统考虑的是西方电视节目，没有考虑孟加拉语和印地语电视节目的推荐系统。然而，地球仪上大约有15亿人对孟加拉语和印地语电视节目感兴趣。考虑到这一事实，在本文中，我们开发了一个推荐系统，可以推荐孟加拉语和印地语电视节目沿着英语电视节目。在我们的框架中，我们使用混合过滤方法推荐电视节目，以获得协同过滤和基于内容的过滤的好处。在找到合适的匹配后，我们向用户推荐top-k电视节目。我们已经进行了几个实验，以显示我们的框架的有效性，并发现它可以推荐有效的推荐电视节目给用户。
Recommendation systems have been actively researched for the last decade and have gained much attention in both research and industry communities. As a result, nowadays we can find recommendations about news, books, movies, products, locations and so on. However, recommendation techniques for TV shows have not been actively researched despite its importance. This is because for developing recommendation systems for TV shows we need to consider two important issues. First, items i.e. TV shows are only available for a certain period of time. Second, a user cannot watch two different shows at the same time. Although there are some recommendation systems for TV shows, most of them consider western TV shows and there is no recommendation system that considers TV shows in Bengali and Hindi. However, around 1500 million people around the globe are interested about Bengali and Hindi TV shows. Considering this fact, in this paper, we develop a recommendation system that can recommend Bengali and Hindi TV shows along with English TV shows. In our framework, we have used hybrid filtering method for recommending TV shows to get the benefit of both collaborative filtering and content-based filtering. After finding appropriate matching we recommend top-k TV shows to the users. We have performed several experiments to show the effectiveness of our framework and found that it can recommend efficient recommendation of TV shows to the users.