Towards Mobile Query Auto-Completion

Zhang, Aston; Goyal, Amit; Baeza-Yates, Ricardo; Chang, Yi; Han, Jiawei; Gunter, Carl A.; Deng, Hongbo

doi:10.1145/2872427.2882977

Cited by 12 publications

(1 citation statement)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[30] further extends this work by predicting queries as search intents from short contexts consisting of previously submitted queries and click data. Authors in [31] do a similar job by considering the search context derived from both the query auto-completion log and the click log (e.g. dwell time, click number, time duration of the click session etc.).…”

Section: A Query Auto-completionmentioning

confidence: 99%

The Role of the User's Browsing and Query History for Improving MPC-generated Query Suggestions

Badarinza

Sterca

Boian

2019

JCOMSS

View full text Add to dashboard Cite

In this paper we present a way of using the very recent user's browsing history and query history, in order to improve the query suggestions mechanism used by an information retrieval system. In order to collect this kind of data, we have built a Chrome browser plugin that monitors user's web activity and stores that data so that we can create a better personal profile for each user. We then analyzed if future queries submitted by a user to the search engine can be predicted from web pages visited by that user in the past (i.e. his recent browsing history) or from queries submitted by that user in the past (i.e. his recent query history). The contribution of this paper is twofold: a) an evaluation of the relevancy of the user's recent browsing and query history to future queries submitted by this user and b) a method for personalizing the query suggestions offered by the Google search engine. More specifically, we are using the user's personal (browsing) history profile in order to reorder query suggestions offered by the Google search engine (i.e. we move query suggestions more relevant to the user's information need to the front positions in the Google provided query suggestions list).Index Terms-information retrieval, query suggestion, query auto-completion, personalized query history.

show abstract

Section: A Query Auto-completionmentioning

confidence: 99%

The Role of the User's Browsing and Query History for Improving MPC-generated Query Suggestions

Badarinza

Sterca

Boian

2019

JCOMSS

View full text Add to dashboard Cite

show abstract

The Impact of User Demographics and Task Types on Cross-App Mobile Search

Aliannejadi

Crestani

Huibers

et al. 2021

Flexible Query Answering Systems

View full text Add to dashboard Cite

User interaction data is an important source of supervision in counterfactual learning to rank (CLTR). Such data suffers from presentation bias. Much work in unbiased learning to rank (ULTR) focuses on position bias, i.e., items at higher ranks are more likely to be examined and clicked. Inter-item dependencies also influence examination probabilities, with outlier items in a ranking as an important example. Outliers are defined as items that observably deviate from the rest and therefore stand out in the ranking. In this paper, we identify and introduce the bias brought about by outlier items: users tend to click more on outlier items and their close neighbors.To this end, we first conduct a controlled experiment to study the effect of outliers on user clicks. Next, to examine whether the findings from our controlled experiment generalize to naturalistic situations, we explore real-world click logs from an e-commerce platform. We show that, in both scenarios, users tend to click significantly more on outlier items than on non-outlier items in the same rankings. We show that this tendency holds for all positions, i.e., for any specific position, an item receives more interactions when presented as an outlier as opposed to a non-outlier item. We conclude from our analysis that the effect of outliers on clicks is a type of bias that should be addressed in ULTR. We therefore propose an outlieraware click model that accounts for both outlier and position bias, called outlier-aware position-based model (OPBM). We estimate click propensities based on OPBM; through extensive experiments performed on both real-world e-commerce data and semi-synthetic data, we verify the effectiveness of our outlier-aware click model. Our results show the superiority of OPBM against baselines in terms of ranking performance and true relevance estimation. CCS CONCEPTS• Information systems → Learning to rank.

show abstract