将评论作为主要研究对象,提出了一种基于事件的新闻客户端热门评论预测框架。为了解决单个新闻客户端数据稀疏的问题,利用新闻客户端的聚集性来挖掘事件;通过建立事件背景解决了使用单条新闻进行预测带来的冷启动问题;框架内部各模块关系完全松耦合,能够依据不同的事件粒度进行在线的热门评论的预测。最后通过实例实验证明,使用框架中提出的联合客户端数据的事件挖掘策略,能够很好地避免单个客户端中数据稀疏的问题,同时证明基于事件进行热门评论框架的效果要优于单纯使用评论本身。
A framework based on event detection is proposed to do popular comments prediction in news Apps.Taking advantage of the aggregation of news Apps,the problem of sparse data for a single news App is avoided.Also,in this framework,events are detected as the context of comments to solve the cold-start problem;components are loosely cou-pled,which means it can adapt all kinds of granularity of events.We provide an instance of this framework and it turns out that using the event detection strategy mentioned above,the sparse data problem no longer exists.What’s more,the framework brings a better prediction result than using the comment itself.