Visual abstraction and ordering in faceted browsing of text collections

Thai, VinhTuan; Handschuh, Siegfried

doi:10.1145/2002353.2002367

Cited by 7 publications

(10 citation statements)

References 13 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To determine similar movies, we utilize the ratings given by other users in the MovieLens 10M dataset and calculate the similarity between the selected movie and all other movies by means of their latent factor vectors (which are determined by a common Matrix Factorization [19] recommender 3 ) using an Euclidean distance metric. This item-based CF approach allows users to take more than just content-related metadata of the items into account, what is often problematic or even not possible in information filtering systems [14,28,30].  Content-based Filtering: For the actor and keyword facet we use conventional content-based recommender methods [25].…”

Section: Facet Types and Corresponding Filtering Methodsmentioning

confidence: 99%

“…Also, it has been criticized that faceted search systems often only allow for conjunctive queries and consider all facets equally important for the user [26,28,30,32]. Furthermore, most approaches perform an exact matching to determine the result set.…”

Section: Interactive Recommendation and Information Filtering Approachesmentioning

confidence: 99%

“…Recent work has also concentrated on user experience of faceted search and has combined it with different visualizations. IVEA [28] uses a matrix visualization to display documents and their relevance according to the selected facets based on TF-IDF heuristics. The facets derived from a user-built ontology can be ordered by the users-although here, the main purpose is to compare document sets in large collections, and the item relevance is not considered for sorting the results.…”

Section: Interactive Recommendation and Information Filtering Approachesmentioning

confidence: 99%

“…Our approach expands the concept of hybrid RS, usually defined as combining different recommender algorithms to increase the accuracy [6], by additionally integrating several interactive filter techniques. However, our point of departure is faceted filtering [34] which has been shown to be an intuitive and efficient technique [18,28] for filtering and browsing large item spaces [14]. Users select concrete filter criteria from different facets which in our approach can represent hard (Boolean) as well as soft (fuzzy) constraints.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Blended Recommending

Loepp

Herrmanny

Ziegler

2015

Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

We present a novel approach that integrates algorithmic recommender techniques with interactive faceted filtering methods. We refer to this approach as blended recommending. It allows users to interact with a set of filter facets representing criteria that can serve as input for different recommendation methods including both collaborative and content-based filtering. Users can select filter criteria from these facets and weight them to express their preferences and to exert control over the hybrid recommendation process. In contrast to hard Boolean filtering, the method aggregates the weighted criteria and calculates a ranked list of recommendations that is visualized and immediately updated when users change the filter settings. Based on this approach, we implemented an interactive movie recommender, MyMovieMixer. In a user study, we compared the system with a conventional faceted filtering system that served as a baseline to obtain insights into user interaction behavior and to assess recommendation quality for our system. The results indicate, among other findings, a higher level of perceived user control, more detailed preference settings, and better suitability when the search goal is vague.

show abstract

Section: Facet Types and Corresponding Filtering Methodsmentioning

confidence: 99%

Section: Interactive Recommendation and Information Filtering Approachesmentioning

confidence: 99%

Section: Interactive Recommendation and Information Filtering Approachesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Blended Recommending

Loepp

Herrmanny

Ziegler

2015

Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…Computational linguistics is providing many of the analytics tools required for the mining of digital texts (e.g. [42,43]). It has been recognized that existing techniques for interaction design in visual analytics rely upon visual metaphors developed more than a decade ago [24] such as dynamic graphs, charts, maps, and plots.…”

Section: Introductionmentioning

confidence: 99%

Omnidirectional 3D Visualization for the Analysis of a Large-Scale Corpus: Tripitaka Koreana

Kenderdine

Lancaster

Lan

et al. 2011

2011 Second International Conference on Culture and Computing

View full text Add to dashboard Cite

This paper presents the research and development of a new omnispatial visualization framework for the collaborative interrogation of the world's largest Buddhist textual canon, using the worlds' first panoramic stereoscopic visualization environment -the Advanced Visualization and Interaction Environment (AVIE). The work is being undertaken at a new research facility, The Applied Laboratory for Interactive Visualization and Embodiment (ALiVE), City University of Hong Kong. The dataset used is the Chinese Buddhist Canon, Koryo version (Tripitaka Koreana) inclassical Chinese, the with 52 million glyphs carved on 83,000 printing blocks in 13th century Korea. The digitized version of this Canon (a project led by University of California Berkeley) contains metadata that links to geospatial positions, contextual images of locations referenced in the text, and to the original rubbings of the wooden blocks. Each character has been abstracted to a 'blue dot' to enable rapid search and pattern visualization. Omnispatial refers to the ability to distribute this data in 360-degrees around the user where the virtually presented visual space is in three dimensions (3D). The project's omnidirectional interactive techniques for corpora representation and interrogation offer a unique framework for enhanced cognition and perception in the analysis of this dataset.

show abstract