Automating Web-Navigation Support Using a Cognitive Model

Aggarwal, Sonal; Oostendorp, Herre van; Indurkhya, Bipin

doi:10.1145/2611040.2611077

Cited by 5 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section we return to the first aim of this article, which in particularly extends our previous conference publication (at WIMS14, [24]): to investigate whether taking into account path adequacy and backtracking strategies next to the semantics of pictures lead to better model performance. For that purpose we will compare and contrast the two models CoLiDeS + Pic and CoLiDeS++Pic.…”

Section: Comparing Model Performance Of Colides + Pic and Colides++picmentioning

confidence: 99%

“…The second aim of this article is to empirically investigate the usefulness of automated model-generated support using the cognitive model. This article mainly differs from our related proceedings paper [24] through emphasizing the modeling part and comparing the performance of different versions of the same model, i.e. a comparison of the CoLiDeS+ and CoLiDeS++Pic model.…”

Section: Introductionmentioning

confidence: 98%

See 1 more Smart Citation

Modeling and Supporting Web-Navigation

Oostendorp

Aggarwal

2015

J Interact Sci

Self Cite

View full text Add to dashboard Cite

Navigation within a website is an important factor for the success of a website. Faster and easy web-navigation leads to better usability and reduces cognitive load on the user. Several cognitive models exist that simulate the web-navigation process. In this paper we propose a new cognitive model -CoLiDeS++Pic (based on Comprehension-based Linked model of Deliberate Search or CoLiDeS) that incorporates path adequacy and backtracking strategies. This model also takes into consideration the semantics of pictures. Firstly, we present here the results of an experiment in which we test the efficacy of support based on the new model CoLiDeS++Pic and multi-tasking under cognitively demanding situations. The results prove that the model-generated support is effective. Secondly, we also propose that in this way navigation behavior can be better modeled when compared to previous models. We verify this hypothesis by simulating the model on a mock-up website and comparing the results with a previous model CoLiDeS+. Extending our previous work we demonstrate that the performance of the new model CoLiDeS++Pic is improved compared to the preceding model CoLiDeS+. We further discuss the challenges and advantages of automating navigation support using the proposed model.

show abstract

Section: Comparing Model Performance Of Colides + Pic and Colides++picmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

Modeling and Supporting Web-Navigation

Oostendorp

Aggarwal

2015

J Interact Sci

Self Cite

View full text Add to dashboard Cite

show abstract

“…The problem of automatic linking of content on the Web has also been studied in the context of wikification, e.g., [34,35,18,43] or entity linking [5,12,23,22], where the goal is to link salient terms (typically named entities) from unnanotated raw text to target knowledge bases such as Wikipedia to provide additional background knowledge to the given text and consequently enrich the reader's experience. In another recent example Aggarwal et al [1] present a tool for automating Web-navigation support that computes semantic similarity between the user goal and the website information. The problem we deal with in this article is substantially different.…”

Section: Related Workmentioning

confidence: 99%

“…Whereas LSA models topics as the results of the factorization of the document-term matrix of a document collection, pLSA and LDA are generative probabilistic models that model each document of a collection as a mixture of topics and a topic as a mixture of words. The Web navigation tool mentioned earlier [1] uses the technique of LSA to compute semantic similarity between the user goal and the website information. To bridge the vocabularies of different domains, pLSA has been used in [54,55].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Latent Dirichlet allocation for linking user-generated content and e-commerce data

Zoghbi

Vulić

Moens

2016

Information Sciences

View full text Add to dashboard Cite

Automatic linking of online content improves navigation possibilities for end users. We focus on linking content generated by users to other relevant sites. In particular, we study the problem of linking information between different usages of the same language, e.g., colloquial and formal idioms or the language of consumers versus the language of sellers. The challenge is that the same items are described using very distinct vocabularies. As a case study, we investigate a new task of linking textual Pinterest.com pins (colloquial) to online webshops (formal). Given this task, our key insight is that we can learn associations between formal and informal language by utilizing aligned data and probabilistic modeling. Specifically, we thoroughly evaluate three different modeling paradigms based on probabilistic topic modeling: monolingual latent Dirichlet allocation (LDA), bilingual LDA (BiLDA) and a novel multi-idiomatic LDA model (MiLDA). We compare these to the unigram model with Dirichlet prior. Our results for all three topic models reveal the usefulness of modeling the hidden thematic structure of the data through topics, as opposed to the linking model based solely on the standard unigram. Moreover, our proposed MiLDA model is able to deal with intrinsic multiidiomatic data by considering the shared vocabulary between the aligned document pairs. The proposed MiLDA obtains the largest stability (less variation with changes in parameters) and highest mean average precision scores in the linking task.

show abstract

Cognitive Modeling of Age and Domain Knowledge Differences in Information Search

Karanam

Oostendorp

2020

Human–Computer Interaction Series

View full text Add to dashboard Cite

Automating Web-Navigation Support Using a Cognitive Model

Cited by 5 publications

References 19 publications

Modeling and Supporting Web-Navigation

Modeling and Supporting Web-Navigation

Latent Dirichlet allocation for linking user-generated content and e-commerce data

Cognitive Modeling of Age and Domain Knowledge Differences in Information Search

Contact Info

Product

Resources

About