“…However, eye movements highly depend on the user characteristics, the task at hand, and the content visualization (Buchanan et al, 2017). Related approaches use eye tracking to infer the perceived relevance of text documents with respect to previously shown trigger questions (Salojarvi et al, 2003(Salojarvi et al, , 2004(Salojarvi et al, , 2005aBuscher et al, 2008a;Loboda et al, 2011;Gwizdka, 2014a;Bhattacharya et al, 2020a,b), and to extend (Buscher et al, 2008b;Chen et al, 2015) or generate search queries (Hardoon et al, 2007;Ajanki et al, 2009). A common disadvantage of approaches for gaze-based relevance estimation is that they are tested using documents with constrained layouts and topics such as single sentences (Salojarvi et al, 2003(Salojarvi et al, , 2004(Salojarvi et al, , 2005a or short news articles that fit on the screen at once (Buscher et al, 2008a;Loboda et al, 2011;Gwizdka, 2014a;Bhattacharya et al, 2020a,b).…”