技术控

    今日:34| 主题:49448
收藏本版 (1)
最新软件应用技术尽在掌握

[其他] Personalized Group Recommendations Are Here

[复制链接]
圈子不同别硬融 发表于 2016-9-30 19:36:27
84 1

立即注册CoLaBug.com会员,免费获得投稿人的专业资料,享用更多功能,玩转个人品牌!

您需要 登录 才可以下载或查看,没有帐号?立即注册

x
There are two primary paradigms for the discovery of digital content. First is the search paradigm, in which the user is actively looking for specific content using search terms and filters (e.g., Google  web search  , Flickr  image search  , Yelp  restaurant search  , etc.). Second is a passive approach, in which the user browses content presented to them (e.g., NYTimes  news  , Flickr  Explore  , and Twitter  trending topics  ). Personalization benefits both approaches by providing relevant content that is tailored to users’ tastes (e.g., Google  News  , Netflix  homepage  , LinkedIn  job search  , etc.). We believe personalization can improve the user experience at Flickr by guiding both new as well as more experienced members as they explore photography. Today, we’re excited to bring you personalized group recommendations.
  Flickr Groups are great for bringing people together around a common theme, be it a style of photography, camera, place, event, topic, or just some fun. Community members join for several reasons—to consume photos, to get feedback, to play games, to get more views, or to start a discussion about photos, cameras, life or the universe. We see value in connecting people with appropriate groups based on their interests. Hence, we decided to start the personalization journey by providing contextually relevant and personalized content that is tuned to each person’s unique taste.
  Of course, in order to respect users’ privacy, group recommendations only consider public photos and public groups. Additionally, recommendations are private to the user. In other words, nobody else sees what is recommended to an individual.
  In this post we describe how we are improving Flickr’s group recommendations. In particular, we describe how we are replacing a curated, non-personalized, static list of groups with a dynamic group recommendation engine that automatically generates new results based on user interactions to provide personalized recommendations unique to each person. The algorithms and backend systems we are building are broad and applicable to other scenarios, such as photo recommendations, contact recommendations, content discovery, etc.
   
Personalized Group Recommendations Are Here-1 (here,we,are,here,we,are,again,here,you,are)

   Figure : Personalized group recommendations
  Challenges

  One challenge of recommendations is determining a user’s interests. These interests could be user-specified, explicit preferences or could be inferred implicitly from their actions, supported by user feedback. For example:
  
       
  • Explicit:
           
    • Ask users what topics interest them     
    • Ask users why they joined a particular group   
       
  • Implicit:
           
    • Infer user tastes from groups they join, photos they like, and users they follow     
    • Infer why users joined a particular group based on their activity, interactions, and dwell time   
       
  • Feedback:
           
    • Get feedback on recommended items when users perform actions such as “Join” or “Follow” or click “Not interested”   
       
  Another challenge of recommendations is figuring out group characteristics. I.e.: what type of group is it? What interests does it serve? What brings Flickr members to this group? We can infer this by analyzing group members, photos posted to the group, discussions and amount of activity in the group.
  Once we have figured out user preferences and group characteristics, recommendations essentially becomes a matchmaking process. At a high-level, we want to support 3 use cases:
  
       
  • Use Case # 1 : Given a group, return all groups that are “similar”   
  • Use Case # 2 : Given a user, return a list of recommended groups   
  • Use Case # 3 : Given a photo, return a list of groups that the photo could belong to  
  Collaborative Filtering

  One approach to recommender systems is presenting similar content in the current context of actions. For example, Amazon’s “Customers who bought this item also bought” or LinkedIn’s “People also viewed.” Item-based collaborative filtering can be used for computing similar items.

Personalized Group Recommendations Are Here-2 (here,we,are,here,we,are,again,here,you,are)

   Figure : Collaborative filtering in action
   By Moshanin (Own work) [  CC BY-SA 3.0  ] from  Wikipedia  
  Intuitively, two groups are similar if they have the same content or same set of users. We observed that users often post the same photo to multiple groups. So, to begin, we compute group similarity based on a photo’s presence in multiple groups.  
   Consider the following sample matrix M ( G i -> P j ) constructed from group photo pools, where 1 means a corresponding group ( G i ) contains an image, and empty (0) means a group does not contain the image.
1234下一页
友荐云推荐




上一篇:Custom Attributes for our Spacing Classes
下一篇:谷歌神经网络翻译系统发布后,我们和Google Brain的工程师聊了聊 ...
酷辣虫提示酷辣虫禁止发表任何与中华人民共和国法律有抵触的内容!所有内容由用户发布,并不代表酷辣虫的观点,酷辣虫无法对用户发布内容真实性提供任何的保证,请自行验证并承担风险与后果。如您有版权、违规等问题,请通过"联系我们"或"违规举报"告知我们处理。

qmyuan 发表于 2016-9-30 22:28:29
突然觉得圈子不同别硬融说的很有道理,赞一个!
回复 支持 反对

使用道具 举报

*滑动验证:
您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

我要投稿

推荐阅读

扫码访问 @iTTTTT瑞翔 的微博
回页顶回复上一篇下一篇回列表手机版
手机版/CoLaBug.com ( 粤ICP备05003221号 | 文网文[2010]257号 )|网站地图 酷辣虫

© 2001-2016 Comsenz Inc. Design: Dean. DiscuzFans.

返回顶部 返回列表