Article Preview
TopIntroduction
Search systems are used to discover information that aids us in our routine tasks, be they leisure or professional. An ideal information system would support the user in exploiting useful information that can be used in steering these primary tasks the user is initiating (Vakkari, 2001). A primary-task can be any cognitively multifaceted practice performed by humans that may invoke information needs- the real-world task, which is the main task one has to carry out (Belkin & Croft, 1992). For example, a user may search ‘Blockchain’ because of a buzzing around, but the system does not know which of the pre-search contexts (the news article) is the prompt cause.
Proactive information retrieval refers to a retrieval strategy that can extract relevant information implicitly without requiring explicit attention or interactions from the user (Li & Belkin, 2008). Primarily employed by modelled user’s search intent by observing the primary search and instantly retrieve information, without actively user to formulate queries (Dumais, Cutrell, Sarin, & Horvitz, 2004). Consequently, Intent estimation from limited primary search input is key challenge, for which traditional system asserts ‘Pre-search’ context (Kong, Zhang, Chang, & Allan, 2015) and user’s tasks (Saastamoinen, 2017), also serve twofold. First, to understand whether a user’s primary task, in contrast to just pre-search browsing history, can be used to predict search intentions, and second, to study if a user utilizes anticipated results and detect the tradeoffs it may offers (Koskela, Luukkonen, Ruotsalo 2018).
The Intent is a topical dimension of user search and characterizes ‘why’ the user is searching, and ‘how’ his search evolves during search progression (Marchionini, 2006). Characteristically, intent defined as ‘immediate reason, purpose, or goal’ that motivates a user to initiate or conduct a search (Nandi & Jagadish, 2011) and co-exist in three aspects, i.e. Pre-search, In-search and Pro-search of the user search context. A significant fraction of user searches is influenced by the user’s primary search aim i.e. ‘Pre-search’ context and others due to intermediate query or result in understanding ‘In-search’ context. An ideal information system would be able to predict the estimation of future intent (also known as ‘Pro-search’ context) based on the captured ‘Pre-search’ and ‘In-search’ context. The prediction of search context of futuristic search ‘Pro-search’ requires identification of co-relations between all three aspects of user search, therefore understanding ‘why’ users start searches and ‘how’ to predict search intent are multifaceted tasks (Van Rijsbergen, 1977; Daoud & Huang, 2013).