scholarly journals Assessing the Quality of Sources in Wikidata Across Languages: A Hybrid Approach

2021 ◽  
Vol 13 (4) ◽  
pp. 1-35
Author(s):  
Gabriel Amaral ◽  
Alessandro Piscopo ◽  
Lucie-aimée Kaffee ◽  
Odinaldo Rodrigues ◽  
Elena Simperl
Keyword(s):  
Machine Learning ◽  
Scale Up ◽  
Hybrid Approach ◽  
Structured Data ◽  
Mixed Methods Study ◽  
Secondary Source ◽  
Ease Of Access ◽  
Large Corpus ◽  
The Web

Wikidata is one of the most important sources of structured data on the web, built by a worldwide community of volunteers. As a secondary source, its contents must be backed by credible references; this is particularly important, as Wikidata explicitly encourages editors to add claims for which there is no broad consensus, as long as they are corroborated by references. Nevertheless, despite this essential link between content and references, Wikidata's ability to systematically assess and assure the quality of its references remains limited. To this end, we carry out a mixed-methods study to determine the relevance, ease of access, and authoritativeness of Wikidata references, at scale and in different languages, using online crowdsourcing, descriptive statistics, and machine learning. Building on previous work of ours, we run a series of microtasks experiments to evaluate a large corpus of references, sampled from Wikidata triples with labels in several languages. We use a consolidated, curated version of the crowdsourced assessments to train several machine learning models to scale up the analysis to the whole of Wikidata. The findings help us ascertain the quality of references in Wikidata and identify common challenges in defining and capturing the quality of user-generated multilingual structured data on the web. We also discuss ongoing editorial practices, which could encourage the use of higher-quality references in a more immediate way. All data and code used in the study are available on GitHub for feedback and further improvement and deployment by the research community.

scholarly journals Improving the Quality of Linked Data Using Statistical Distributions

2018 ◽  
pp. 1638-1664 ◽  
Author(s):  
Heiko Paulheim ◽  
Christian Bizer
Keyword(s):  
Knowledge Base ◽  
Linked Data ◽  
Relational Databases ◽  
Knowledge Bases ◽  
Structured Data ◽  
Data Sources ◽  
Data Sets ◽  
Statistical Distributions ◽  
The Web

Linked Data on the Web is either created from structured data sources (such as relational databases), from semi-structured sources (such as Wikipedia), or from unstructured sources (such as text). In the latter two cases, the generated Linked Data will likely be noisy and incomplete. In this paper, we present two algorithms that exploit statistical distributions of properties and types for enhancing the quality of incomplete and noisy Linked Data sets: SDType adds missing type statements, and SDValidate identifies faulty statements. Neither of the algorithms uses external knowledge, i.e., they operate only on the data itself. We evaluate the algorithms on the DBpedia and NELL knowledge bases, showing that they are both accurate as well as scalable. Both algorithms have been used for building the DBpedia 3.9 release: With SDType, 3.4 million missing type statements have been added, while using SDValidate, 13,000 erroneous RDF statements have been removed from the knowledge base.

scholarly journals Technologies for Complex Intelligent Clinical Data Analysis

2016 ◽  
Vol 71 (2) ◽  
pp. 160-171 ◽  
Author(s):  
A. A. Baranov ◽  
L. S. Namazova-Baranova ◽  
I. V. Smirnov ◽  
D. A. Devyatkin ◽  
A. O. Shelmanov ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Analysis ◽  
Chronic Diseases ◽  
Clinical Information ◽  
Structured Data ◽  
Unstructured Data ◽  
Intelligent Analysis ◽  
Pediatric Center

The paper presents the system for intelligent analysis of clinical information. Authors describe methods implemented in the system for clinical information retrieval, intelligent diagnostics of chronic diseases, patient’s features importance and for detection of hidden dependencies between features. Results of the experimental evaluation of these methods are also presented.Background: Healthcare facilities generate a large flow of both structured and unstructured data which contain important information about patients. Test results are usually retained as structured data but some data is retained in the form of natural language texts (medical history, the results of physical examination, and the results of other examinations, such as ultrasound, ECG or X-ray studies). Many tasks arising in clinical practice can be automated applying methods for intelligent analysis of accumulated structured array and unstructured data that leads to improvement of the healthcare quality.Aims: the creation of the complex system for intelligent data analysis in the multi-disciplinary pediatric center.Materials and methods: Authors propose methods for information extraction from clinical texts in Russian. The methods are carried out on the basis of deep linguistic analysis. They retrieve terms of diseases, symptoms, areas of the body and drugs. The methods can recognize additional attributes such as «negation» (indicates that the disease is absent), «no patient» (indicates that the disease refers to the patient’s family member, but not to the patient), «severity of illness», «disease course», «body region to which the disease refers». Authors use a set of hand-drawn templates and various techniques based on machine learning to retrieve information using a medical thesaurus. The extracted information is used to solve the problem of automatic diagnosis of chronic diseases. A machine learning method for classification of patients with similar nosology and the method for determining the most informative patients’ features are also proposed.Results: Authors have processed anonymized health records from the pediatric center to estimate the proposed methods. The results show the applicability of the information extracted from the texts for solving practical problems. The records of patients with allergic, glomerular and rheumatic diseases were used for experimental assessment of the method of automatic diagnostic. Authors have also determined the most appropriate machine learning methods for classification of patients for each group of diseases, as well as the most informative disease signs. It has been found that using additional information extracted from clinical texts, together with structured data helps to improve the quality of diagnosis of chronic diseases. Authors have also obtained pattern combinations of signs of diseases.Conclusions: The proposed methods have been implemented in the intelligent data processing system for a multidisciplinary pediatric center. The experimental results show the availability of the system to improve the quality of pediatric healthcare. 

scholarly journals Measuring the quality of scientific references in Wikipedia: an analysis of more than 115M citations to over 800,000 scientific articles

2020 ◽  
Author(s):  
Joshua M. Nicholson ◽  
Ashish Uppala ◽  
Matthias Sieber ◽  
Peter Grabitz ◽  
Milo Mordaunt ◽  
...  
Keyword(s):  
Machine Learning ◽  
Web Of Science ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Supporting Evidence ◽  
Novel Technique ◽  
Wide Variability ◽  
The Web ◽  
Massive Database

AbstractWikipedia is a widely used online reference work which cites hundreds of thousands of scientific articles across its entries. The quality of these citations has not been previously measured, and such measurements have a bearing on the reliability and quality of the scientific portions of this reference work. Using a novel technique, a massive database of qualitatively described citations, and machine learning algorithms, we analyzed 1,923,575 Wikipedia articles which cited a total of 824,298 scientific articles, and found that most scientific articles (57%) are uncited or untested by subsequent studies, while the remainder show a wide variability in contradicting or supporting evidence (2-41%). Additionally, we analyzed 51,804,643 scientific articles from journals indexed in the Web of Science and found that most (85%) were uncited or untested by subsequent studies, while the remainder show a wide variability in contradicting or supporting evidence (1-14%).

A Comparative Study of XML Change Detection Algorithms

2010 ◽  
pp. 22-38 ◽  
Author(s):  
Grégory Cobéna ◽  
Talel Abdessalem
Keyword(s):  
Comparative Study ◽  
Change Detection ◽  
Structured Data ◽  
Formal Definition ◽  
Version Management ◽  
Xml Data ◽  
Detection Algorithms ◽  
Change Detection Algorithms ◽  
The Web

Change detection is an important part of version management for databases and document archives. The success of XML has recently renewed interest in change detection on trees and semi-structured data, and various algorithms have been proposed. We study different algorithms and representations of changes based on their formal definition and on experiments conducted over XML data from the Web. Our goal is to provide an evaluation of the quality of the results, the performance of the tools and, based on this, guide the users in choosing the appropriate solution for their applications.

User and Context-Aware Quality Filters Based on Web Metadata Retrieval

2011 ◽  
pp. 167-193 ◽  
Author(s):  
Ricardo Barros ◽  
Geraldo Xexéo ◽  
Wallace A. Pinheiro ◽  
Jano de Souza
Keyword(s):  
Information Needs ◽  
Initial Evaluation ◽  
Context Aware ◽  
Web Information ◽  
Precise Knowledge ◽  
Ease Of Access ◽  
User Perspectives ◽  
Context Characteristics ◽  
The Web

Due to the amount of information on the Web being so large and being of varying levels of quality, it is becoming increasingly difficult to find precisely what is required on the Web, particularly if the information consumer does not have precise knowledge of his or her information needs. On the Web, while searching for information, users can find data that is old, imprecise, invalid, intentionally wrong, or biased, due to this large amount of available data and comparative ease of access. In this environment users constantly receive useless, outdated, or false data, which they have no means to assess. This chapter addresses the issues regarding the large amount and low quality of Web information by proposing a methodology that adopts user and context-aware quality filters based on Web metadata retrieval. This starts with an initial evaluation and adjusts it to consider context characteristics and user perspectives to obtain aggregated evaluation values.

scholarly journals A deep learning based technique for plagiarism detection: a comparative study

2020 ◽  
Vol 9 (1) ◽  
pp. 81
Author(s):  
Hambi El Mostafa ◽  
Faouzia Benabbou
Keyword(s):  
Deep Learning ◽  
Comparative Study ◽  
Access To Information ◽  
Vector Representation ◽  
Plagiarism Detection ◽  
Representation Method ◽  
Ease Of Access ◽  
Similarity Method ◽  
The Web

<table width="0" border="1" cellspacing="0" cellpadding="0"><tbody><tr><td valign="top" width="593"><p>The ease of access to the various resources on the web-enabled the democratization of access to information but at the same time allowed the appearance of enormous plagiarism problems. Many techniques of plagiarism were identified in the literature, but the plagiarism of idea steels the foremost troublesome to detect, because it uses different text manipulation at the same time. Indeed, a few strategies have been proposed to perform semantic plagiarism detection, but they are still numerous challenges to overcome. Unlike the existing states of the art, the purpose of this study is to give an overview of different propositions for plagiarism detection based on the deep learning algorithms. The main goal of these approaches is to provide a high quality of worlds or sentences vector representation. In this paper, we propose a comparative study based on a set of criterions like: Vector representation method, Level Treatment, Similarity Method and Dataset. One result of this study is that most of researches are based on world granularity and use the word2vec method for word vector representation, which sometimes is not suitable to keep the meaning of the whole sentences. Each technique has strengths and weaknesses; however, none is quite mature for semantic plagiarism detection.</p></td></tr></tbody></table>

scholarly journals Improving the Quality of Linked Data Using Statistical Distributions

2014 ◽  
Vol 10 (2) ◽  
pp. 63-86 ◽  
Author(s):  
Heiko Paulheim ◽  
Christian Bizer
Keyword(s):  
Knowledge Base ◽  
Linked Data ◽  
Relational Databases ◽  
Knowledge Bases ◽  
Structured Data ◽  
Data Sources ◽  
Data Sets ◽  
Statistical Distributions ◽  
The Web

Linked Data on the Web is either created from structured data sources (such as relational databases), from semi-structured sources (such as Wikipedia), or from unstructured sources (such as text). In the latter two cases, the generated Linked Data will likely be noisy and incomplete. In this paper, we present two algorithms that exploit statistical distributions of properties and types for enhancing the quality of incomplete and noisy Linked Data sets: SDType adds missing type statements, and SDValidate identifies faulty statements. Neither of the algorithms uses external knowledge, i.e., they operate only on the data itself. We evaluate the algorithms on the DBpedia and NELL knowledge bases, showing that they are both accurate as well as scalable. Both algorithms have been used for building the DBpedia 3.9 release: With SDType, 3.4 million missing type statements have been added, while using SDValidate, 13,000 erroneous RDF statements have been removed from the knowledge base.

scholarly journals Machine Learning on Graph-Structured Data

2021 ◽  
Author(s):  
Claudio D. T. Barros ◽  
Daniel N. R. da Silva ◽  
Fabio A. M. Porto
Keyword(s):  
Machine Learning ◽  
Biological Networks ◽  
Representation Learning ◽  
Structured Data ◽  
Graph Classification ◽  
Open Problems ◽  
Continuous Increase ◽  
Knowledge Graphs ◽  
Traditional Approaches

Several real-world complex systems have graph-structured data, including social networks, biological networks, and knowledge graphs. A continuous increase in the quantity and quality of these graphs demands learning models to unlock the potential of this data and execute tasks, including node classification, graph classification, and link prediction. This tutorial presents machine learning on graphs, focusing on how representation learning - from traditional approaches (e.g., matrix factorization and random walks) to deep neural architectures - fosters carrying out those tasks. We also introduce representation learning over dynamic and knowledge graphs. Lastly, we discuss open problems, such as scalability and distributed network embedding systems.

scholarly journals A supervised scheme for aspect extraction in sentiment analysis using the hybrid feature set of word dependency relations and lemmas

2021 ◽  
Vol 7 ◽  
pp. e347
Author(s):  
Bhavana R. Bhamare ◽  
Jeyanthi Prabhu
Keyword(s):  
Social Media ◽  
Feature Selection ◽  
Sentiment Analysis ◽  
Hybrid Approach ◽  
Structured Data ◽  
Unstructured Data ◽  
Aspect Extraction ◽  
Dependency Relation ◽  
Dependency Relations ◽  
The Web

Due to the massive progression of the Web, people post their reviews for any product, movies and places they visit on social media. The reviews available on social media are helpful to customers as well as the product owners to evaluate their products based on different reviews. Analyzing structured data is easy as compared to unstructured data. The reviews are available in an unstructured format. Aspect-Based Sentiment Analysis mines the aspects of a product from the reviews and further determines sentiment for each aspect. In this work, two methods for aspect extraction are proposed. The datasets used for this work are SemEval restaurant review dataset, Yelp and Kaggle datasets. In the first method a multivariate filter-based approach for feature selection is proposed. This method support to select significant features and reduces redundancy among selected features. It shows improvement in F1-score compared to a method that uses only relevant features selected using Term Frequency weight. In another method, selective dependency relations are used to extract features. This is done using Stanford NLP parser. The results gained using features extracted by selective dependency rules are better as compared to features extracted by using all dependency rules. In the hybrid approach, both lemma features and selective dependency relation based features are extracted. Using the hybrid feature set, 94.78% accuracy and 85.24% F1-score is achieved in the aspect category prediction task.

scholarly journals Contextual Autocomplete: A Novel User Interface Using Machine Learning to Improve Ontology Usage and Structured Data Capture for Presenting Problems in the Emergency Department

2017 ◽  
Author(s):  
Nathaniel R. Greenbaum ◽  
Yacine Jernite ◽  
Yoni Halpern ◽  
Shelley Calder ◽  
Larry A. Nathanson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Emergency Department ◽  
User Interface ◽  
Vital Signs ◽  
Structured Data ◽  
Data Capture ◽  
Free Text ◽  
Presenting Problems ◽  
Before And After

AbstractObjectiveTo determine the effect of contextual autocomplete, a user interface that uses machine learning, on the efficiency and quality of documentation of presenting problems (chief complaints) in the emergency department (ED).Materials and MethodsWe used contextual autocomplete, a user interface that ranks concepts by their predicted probability, to help nurses enter data about a patient’s reason for visiting the ED. Predicted probabilities were calculated using a previously derived model based on triage vital signs and a brief free text note. We evaluated the percentage and quality of structured data captured using a prospective before-and-after study design.ResultsA total of 279,231 patient encounters were analyzed. Structured data capture improved from 26.2% to 97.2% (p<0.0001). During the post-implementation period, presenting problems were more complete (3.35 vs 3.66; p=0.0004), as precise (3.59 vs. 3.74; p=0.1), and higher in overall quality (3.38 vs. 3.72; p=0.0002). Our system reduced the mean number of keystrokes required to document a presenting problem from 11.6 to 0.6 (p<0.0001), a 95% improvement.DiscussionWe have demonstrated a technique that captures structured data on nearly all patients. We estimate that our system reduces the number of man-hours required annually to type presenting problems at our institution from 92.5 hours to 4.8 hours.ConclusionImplementation of a contextual autocomplete system resulted in improved structured data capture, ontology usage compliance, and data quality.

Sign in / Sign up

Export Citation Format

Share Document