On the right track! Analysing and Predicting Navigation Success in Wikipedia

Understanding and modeling user navigation behaviour in the web is of interest for different applications. For example, e-commerce portals can be adjusted to strengthen customer engagement or information sites can be optimized to improve the availability of relevant content to the user. In web navigation, the users goal and whether she reached it, is typically unknown. This makes navigation games particularly interesting to researchers, since they capture human navigation towards a known goal and allowbuilding labelled datasets suitable for supervised machine learning models. In this work, we show that a recurrent neural network model can predict game success from a partial click trail without knowledge of the users navigation goal. We evaluate our approach on data from WikiSpeedia and WikiGame, two well known navigation games and achieve an AUC of 86% and 90%, respectively. Furthermore, we show that our model outperforms a baseline that leverages the navigation goal on the WikiSpeedia dataset. A detailed analysis of both datasets with regards to structural and content related properties reveals significant differences in navigation behaviour, which confirms the applicability of our approach to different settings.

[1]  Fabian Flöck,et al.  Query for Architecture, Click through Military: Comparing the Roles of Search and Navigation on Wikipedia , 2018, WebSci.

[2]  Lei Han,et al.  All Those Wasted Hours: On Task Abandonment in Crowdsourcing , 2019, WSDM.

[3]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[4]  Ryen W. White,et al.  Leaving so soon?: understanding and predicting web search abandonment rationales , 2012, CIKM.

[5]  Quoc V. Le,et al.  Document Embedding with Paragraph Vectors , 2015, ArXiv.

[6]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[7]  Ryen W. White,et al.  Assessing the scenic route: measuring the value of search trails in web logs , 2010, SIGIR.

[8]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[9]  Jane Li,et al.  Good abandonment in mobile and PC internet search , 2009, SIGIR.

[10]  Sreenivas Gollapudi,et al.  Bypass rates: reducing query abandonment using negative inferences , 2008, KDD.

[11]  Reinhold Scherer,et al.  Models of human navigation in information networks based on decentralized search , 2013, HT.

[12]  Jure Leskovec,et al.  Why We Read Wikipedia , 2017, WWW.

[13]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[14]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[15]  Jure Leskovec,et al.  Human wayfinding in information networks , 2012, WWW.

[16]  Christoph Trattner,et al.  Exploring Differences and Similarities between Hierarchical Decentralized Search and Human Navigation in Information Networks , 2012 .

[17]  Mingzhe Wang,et al.  LINE: Large-scale Information Network Embedding , 2015, WWW.

[18]  Andreas Hotho,et al.  Computing Semantic Relatedness from Human Navigational Paths: A Case Study on Wikipedia , 2013, Int. J. Semantic Web Inf. Syst..

[19]  Jure Leskovec,et al.  Mining Missing Hyperlinks from Human Navigation Traces: A Case Study of Wikipedia , 2015, WWW.

[20]  Kyunghyun Cho,et al.  End-to-End Goal-Driven Web Navigation , 2016, NIPS.

[21]  Jure Leskovec,et al.  Automatic Versus Human Navigation in Information Networks , 2012, ICWSM.

[22]  Kilian Q. Weinberger,et al.  On Calibration of Modern Neural Networks , 2017, ICML.

[23]  Andreas Hotho,et al.  Learning Semantic Relatedness from Human Feedback Using Relative Relatedness Learning , 2017, International Semantic Web Conference.

[24]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[25]  Jure Leskovec,et al.  The last click: why users give up information network navigation , 2014, WSDM.

[26]  Dan Morris,et al.  Investigating the querying and browsing behavior of advanced search engine users , 2007, SIGIR.

[27]  Andreas Hotho,et al.  Extracting Semantics from Random Walks on Wikipedia: Comparing Learning and Counting Methods , 2021, Wiki@ICWSM.

[28]  Kristina Lerman,et al.  How the structure of Wikipedia articles influences user navigation , 2016, New Rev. Hypermedia Multim..

[29]  Mark S. Ackerman,et al.  The perfect search engine is not enough: a study of orienteering behavior in directed search , 2004, CHI.