检索结果-内蒙古大学图书馆

It’s Time to Consider ‘Time’ when Evaluating Recommender-System Algorithms [Proposal]

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Beel, Joeran Trinity College Dublin Department of Computer Science and Statistics Knowledge and Data Engineering Group ADAPT Centre Ireland

In this position paper, we question the current practice of calculating evaluation metrics for recommender systems as single numbers (e.g. precision p=.28 or mean absolute error MAE = 1.21). We argue that single numbers express only average effectiveness over usually a rather long period (e.g. a year or even longer). This practice provides only a vague and static view of the data. We propose that recommender-system researchers should instead calculate metrics for time-series such as weeks or months, and plot the results in e.g. a line chart. This way, results show how algorithms’ effectiveness develops over time, and hence the results allow drawing more meaningful conclusions about how an algorithm will perform in the future. In this paper, we explain our reasoning, provide an example to illustrate our reasoning and present suggestions for what the community should do next. Copyright © 2017, The Authors. All rights reserved.

关键词： Recommender systems

Mining social media to inform peatland fire and haze disaster management

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Kibanov, Mark Stumme, Gerd Amin, Imaduddin Lee, Jong Gun Knowledge & Data Engineering Group ITeG Research Center University of Kassel Germany Pulse Lab Jakarta UN Global Pulse United Nations

Peatland fires and haze events are disasters with national, regional, and international implications. The phenomena lead to direct damage to local assets, as well as broader economic and environmental losses. Satellite imagery is still the main and often the only available source of information for disaster management. In this article, we test the potential of social media to assist disaster management. To this end, we compare insights from two datasets: fire hotspots detected via NASA satellite imagery and almost all GPS-stamped tweets from Sumatra Island, Indonesia, posted during 2014. Sumatra Island is chosen as it regularly experiences a significant number of haze events, which affect citizens in Indonesia as well as in nearby countries including Malaysia and Singapore. We analyse temporal correlations between the datasets and their geo-spatial interdependence. Furthermore, we show how Twitter data reveals changes in users’ behavior during severe haze events. Overall, we demonstrate that social media are a valuable source of complementary and supplementary information for haze disaster management. Based on our methodology and findings, an analytics tool to improve peatland fire and haze disaster management by the Indonesian authorities is under development. Copyright © 2017, The Authors. All rights reserved.

关键词： Wetlands

Exploring choice overload in related-article recommendations in digital libraries 5

学校读者我要写书评

暂无评论

Exploring choice overload in related-article recommendations...

5th Workshop on Bibliometric-Enhanced Information Retrieval, BIR 2017

作者： Beierle, Felix Aizawa, Akiko Beel, Joeran Service-centric Networking Technische Universität Berlin Telekom Innovation Laboratories Berlin Germany Digital Content and Media Sciences Research Division Tokyo Japan Trinity College Dublin School of Computer Science and Statistics Intelligent Systems Discipline Knowledge and Data Engineering Group ADAPT Centre Dublin Ireland

We investigate the problem of choice overload - the difficulty of making a decision when faced with many options - when displaying related-article recommendations in digital libraries. So far, research regarding to how many items should be displayed has mostly been done in the fields of media recommendations and search engines. We analyze the number of recommendations in current digital libraries. When browsing fullscreen with a laptop or desktop PC, all display a fixed number of recommendations. 72% display three, four, or five recommendations, none display more than ten. We provide results from an empirical evaluation conducted with GESIS' digital library Sowiport, with recommendations delivered by recommendations-as-a-service provider Mr. DLib. We use click-through rate as a measure of recommendation effectiveness based on 3.4 million delivered recommendations. Our results show lower click-through rates for higher numbers of recommendations and twice as many clicked recommendations when displaying ten instead of one related-articles. Our results indicate that users might quickly feel overloaded by choice. © 2017, CEUR-WS. All rights reserved.

关键词： Digital libraries

Describing reasoning results with RVO, the reasoning violations ontology 2

学校读者我要写书评

暂无评论

Describing reasoning results with RVO, the reasoning violati...

2nd Workshop on Managing the Evolution and Preservation of the data Web, MEPDaW 2016 and the 3rd Workshop on Linked data Quality, LDQ 2016

作者： Božić, Bojan Brennan, Rob Feeney, Kevin C. Mendel-Gleason, Gavin Knowledge and Data Engineering Group Trinity College Dublin College Green Dublin 2 Ireland

This paper presents a new OWL RL ontology, the Reasoning Violations Ontology (RVO), which describes both ABox and TBox reasoning errors produced by DL reasoners. This is to facilitate the integration of reasoners into data engineering tool-chains. The ontology covers violations of OWL 2 direct semantics and syntax detected on both the schema and instance level over the full range of OWL 2 and RDFS language constructs. Thus it is useful for reporting results to other tools when a reasoner is applied to linked data, RDFS vocabularies or OWL ontologies, for example for quality evaluations such as consistency, completeness or integrity. RVO supports supervised or semi-supervised error localisation and repair by defining properties that both identify the statement or triple where a violation is detected, and by providing context information on the violation which may help the repair process. In a case study we show how the ontology can be used by a reasoner and a supervised repair process to accelerate high quality ontology development and provide automated constraint checking feedback on instance data. RVO is also being used to enable integration of reasoning results into multi-vendor data quality tool chains within the ALIGNED H2020 project.

关键词： Ontology

Towards collaborative conceptual exploration

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Hanika, Tom Zumbrägel, Jens Knowledge and Data Engineering Group University of Kassel Germany Interdisciplinary Research Center for Information System Design University of Kassel Germany Faculty of Computer Science and Mathematics University of Passau Germany

In domains with high knowledge distribution a natural objective is to create principle foundations for collaborative interactive learning environments. We present a first mathematical characterization of a collaborative learning group, a consortium, based on closure systems of attribute sets and the well-known attribute exploration algorithm from formal concept analysis. To this end, we introduce (weak) local experts for subdomains of a given knowledge domain. These entities are able to refute and potentially accept a given (implicational) query for some closure system that is a restriction of the whole domain. On this we build up a consortial expert and show first insights about the ability of such an expert to answer queries. Furthermore, we depict techniques on how to cope with falsely accepted implications and on combining counterexamples. Using notions from combinatorial design theory we further expand those insights as far as providing first results on the decidability problem if a given consortium is able to explore some target domain. Applications in conceptual knowledge acquisition as well as in collaborative interactive ontology learning are at *** Codes 03G10 68T27 Copyright © 2017, The Authors. All rights reserved.

关键词： Learning systems

The Linked data Mining Challenge 2016 5

学校读者我要写书评

暂无评论

The Linked Data Mining Challenge 2016

5th Joint Workshop on data Mining and knowledge Discovery meets Linked Open data and the 1st International Workshop on Completing and Debugging the Semantic Web, Know@LOD 2016 and CoDeS 2016

作者： Ristoski, Petar Paulheim, Heiko Svátek, Vojtěch Zeman, Václav University of Mannheim Research Group Data and Web Science Germany University of Economics Department of Information and Knowledge Engineering Prague Czech Republic

The 2016 edition of the Linked data Mining Challenge, conducted in conjunction with Know@LOD 2016, has been the fourth edition of this challenge. This year's dataset collected music album ratings, where the task was to classify well and badly rated music albums. The best solution submitted reached an accuracy of almost 92:5%, which is a clear advancement over the baseline of 69:38%.

关键词： Linked data

Adaptive kNN using expected accuracy for classification of geo-spatial data

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Kibanov, Mark Atzmueller, Martin Becker, Martin Hotho, Andreas Mueller, Juergen Stumme, Gerd University of Kassel ITeG Center Knowledge and Data Engineering Wilhelmshöher Allee 73 Kassel34121 Tilburg University WarandelaanTilburg5037 AB Netherlands University of Würzburg DMIR Group Am Hubland Würzburg97074 Germany

The k-Nearest Neighbor (kNN) classification approach is conceptually simple – yet widely applied since it often performs well in practical applications. However, using a global constant k does not always provide an optimal solution, e. g., for datasets with an irregular density distribution of data points. This paper proposes an adaptive kNN classifier where k is chosen dynamically for each instance (point) to be classified, such that the expected accuracy of classification is maximized. We define the expected accuracy as the accuracy of a set of structurally similar observations. An arbitrary similarity function can be used to find these observations. We introduce and evaluate different similarity functions. For the evaluation, we use five different classification tasks based on geo-spatial data. Each classification task consists of (tens of) thousands of items. We demonstrate, that the presented expected accuracy measures can be a good estimator for kNN performance, and the proposed adaptive kNN classifier outperforms common kNN and previously introduced adaptive kNN algorithms. Also, we show that the range of considered k can be significantly reduced to speed up the algorithm without negative influence on classification accuracy. Copyright © 2017, The Authors. All rights reserved.

关键词： Classification (of information)

On the usability of probably approximately correct implication bases

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Borchmann, Daniel Hanika, Tom Obiedkov, Sergei Chair of Automata Theory Technische Universität Dresden Germany Knowledge & Data Engineering Group University of Kassel Germany Interdisciplinary Research Center for Information System Design University of Kassel Germany National Research University Higher School of Economics Moscow Russia

We revisit the notion of probably approximately correct implication bases from the literature and present a first formulation in the language of formal concept analysis, with the goal to investigate whether such bases represent a suitable substitute for exact implication bases in practical use-cases. To this end, we quantitatively examine the behavior of probably approximately correct implication bases on artificial and real-world data sets and compare their precision and recall with respect to their corresponding exact implication bases. Using a small example, we also provide qualitative insight that implications from probably approximately correct bases can still represent meaningful knowledge from a given data *** Codes 03G10 68T27 Copyright © 2017, The Authors. All rights reserved.

关键词： Formal concept analysis

Some experimental results on randomly generating formal contexts 13

学校读者我要写书评

暂无评论

Some experimental results on randomly generating formal cont...

13th International Conference on Concept Lattices and Their Applications, CLA 2016

作者： Borchmann, Daniel Hanika, Tom Automata Theory Technische Universität Dresden Germany Center for Advancing Electronics Dresden Technische Universität Dresden Germany Knowledge and Data Engineering Group University of Kassel Germany

We investigate different simple approaches to generate random formal contexts. To this end, we consider for each approach the empirical correlation between the number of intents and pseudo-intents. We compare the results of these experiments with corresponding observations on real-world use-cases. This comparison yields huge differences between artificially generated and real-world data sets, indicating that using randomly generated formal contexts for applications such as benchmarking may not necessarily be meaningful. In doing so, we additionally show that the previously observed phenomenon of the "Stegosaurus" does not express a real correlation between intents and pseudo-intents, but is an artifact of the way random contexts are generated.

关键词： Formal concept analysis