文本飘红策略对搜索引擎用户行为的影响

Effect of snippet text bolding in search user behavior

搜索用户根据搜索引擎结果页面的搜索结果来决定他们是否点击特定的网页,其展示形式在用户整个搜索交互过程中起到重要作用。查询词飘红是目前商业搜索引擎结果文本主要采用的展现形式,存在着满篇红和缺乏有用信息的现象,该文旨在提出一种新的飘红策略,从而提高用户的搜索效率。该文基于人工标注的结果提出了3种文本飘红策略,分别是缩减查询词飘红策略、任务级飘红策略和结果级飘红策略,通过实验分析了4种不同的摘要飘红策略对用户搜索行为的影响,结果表明：该文提出的3种文本飘红策略,其性能均优于目前商业引擎采用的查询词飘红策略,通过控制飘红次数、飘红比例和提供有价值的信息,可以对用户搜索行为产生非常积极的影响。

Search users rely on result captions including titles,snippets and URLs to decide whether they should click a particular result.Snippets usually serve as a query-dependent summary of its corresponding landing page and are,therefore,one of the most important factors in the search interaction process.At present,commercial search engines use query bolding strategies,but these have various problems and lack useful information.This paper presents a bolding strategy that improves user search efficiency.The method includes three bolding strategies based on crowd sourcing results which differ from the query terms strategy.Tests show that the search behavior is affected by the term bolding strategies without changes in the snippet contents.The tests also show that the responses to the three bolding strategies are better than responses to the query terms bolding strategy to produce a better bolding strategy.The appropriate bolding numbers,bolding ratio,and targeted information have a very positive impact on the user＇s search behavior.