Filters








9,397 Hits in 2.5 sec

Ontology boosted deep learning for disease name extraction from Twitter messages

Mark Abraham Magumba, Peter Nabende, Ernest Mwebaze
2018 Journal of Big Data  
based deep learning approach for extracting disease names from Twitter messages.  ...  The significance of this development is that it can potentially reduce the cost of generating named entity recognition models by reducing the cost of annotating training data since ontology creation is  ...  Availability of data and materials The best performing Keras HDF5 LSTM model and the datasets are available this Google drive folder: https ://drive .googl e.com/open?  ... 
doi:10.1186/s40537-018-0139-2 fatcat:4ccvaoywzvbcxm5swrv2elwbam

Twitter Fake Account Detection and Classification using Ontological Engineering and Semantic Web Rule Language

MOHAMMED JABARDI, Asaad Sabah Hadi
2020 Karbala International Journal of Modern Science  
Web Ontology Language (OWL), Semantic Web Rule Language (SWRL) rules, and reasoners are deployed to inductively learn the rules that distinguish a fake account (bot) from a real one, as well as to classify  ...  Nowadays, Twitter has become one of the fastest-growing Online Social Networks (OSNs) for data sharing frameworks and microblogging.  ...  The data set included 11,737 Twitter Fig. 3 . SWRL rule for inferring new knowledge "Reliable" class membership.  ... 
doi:10.33640/2405-609x.2285 fatcat:yja3hpipnrawpcqlayxon67oke

Ontology Meter for Twitter Fake Accounts Detection

Mohammed Jabardi, University of Babylon, Asaad Hadi, University of Babylon
2021 International Journal of Intelligent Engineering and Systems  
This study presents a new approach to detect fake Twitter accounts using ontology and Semantic Web Rule Language (SWRL) rules.  ...  Twitter is an open application programming interface and thus vulnerable to attack from fake accounts, which are primarily created for advertisement and marketing, defamation of an individual, consumer  ...  from the data.  ... 
doi:10.22266/ijies2021.0228.38 fatcat:2vioogdwyzcyxczbjwcbu24v3e

Online Presence in Adaptive Learning on the Social Semantic Web

Jelena Jovanovic, Dragan Gasevic, Milan Stankovic, Zoran Jeremic, Melody Siadaty
2009 2009 International Conference on Computational Science and Engineering  
In adaptive learning environments, this exchange of online presence data cannot be considered isolated from the overall learning context.  ...  To address this issue, we propose an ontology-based approach to sharing online presence data in adaptive learning environments through the use of the Online Presence Ontology.  ...  Accessing her OPO-based online presence data, the system learns that she is 'away' (from her online status), but also that she is in the same building as Tom (from her current location data).  ... 
doi:10.1109/cse.2009.286 dblp:conf/cse/JovanovicGSJS09 fatcat:ibywq3qodfguzomgrhfgtphv6a

New Approach of Measuring Human Personality Traits Using Ontology-Based Model from Social Media Data

Andry Alamsyah, Nidya Dudija, Sri Widiyanesti
2021 Information  
Our first contribution is to develop the Big Five personality trait-based model to detect human personalities from their textual data in the Indonesian language.  ...  The model uses an ontology approach instead of the more famous machine learning model. The former better captures the meaning and intention of phrases and words in the domain of human personality.  ...  Data Availability Statement: Not Applicable Conflicts of Interest: The authors declare no conflicts of interest.  ... 
doi:10.3390/info12100413 fatcat:3xzmfa6nkffntfwo6d7ruryhxe

Constructing Differentiated Educational Materials Using Semantic Annotation for Sustainable Education in IoT Environments

Yongsung Kim, Jihoon Moon, Eenjun Hwang
2018 Sustainability  
Such interaction data can be collected through the physical devices to define personal data.  ...  For instance, in education, this technology contributes to improving learning efficiency in the class by enabling learners to interact with physical devices and providing appropriate learning content based  ...  Jihoon Moon collected experimental data, processed the data and visualized the experimental results. Eenjun Hwang conceived and supervised the work.  ... 
doi:10.3390/su10041296 fatcat:qzunrir4mfe7hlssjcwm66xgka

A User-Centric Approach for Social Data Integration and Recommendation

Yuan Wang, Jie Zhang, Julita Vassileva
2010 2010 3rd International Conference on Human-Centric Computing  
We propose a usercentric approach for integrating social data from different social networking sites and allowing users to create personalized social and semantic contexts for their social data.  ...  The retrieved data about friends and their activities from Twitter and Facebook are translated into our generic ontology that combines FOAF and Activity Stream standards together.  ...  In this work, we designed a generic ontology to describe social data from different social networking sites.  ... 
doi:10.1109/humancom.2010.5563331 fatcat:oz5sqypwkzcztnjckfctkfcncq

Augmenting Lightweight Domain Ontologies with Social Evidence Sources

Albert Weichselbraun, Gerhard Wohlgenannt, Arno Scharl
2010 2010 Workshops on Database and Expert Systems Applications  
Data from social sources such as Delicious, Flickr, Technorati and Twitter provide an outside view of the domain and help incorporate external knowledge into the ontology learning process.  ...  This paper presents an approach to augment corpus-based ontology learning by considering terms from collaborative tagging systems, social networking platforms, and micro-blogging services.  ...  The authors would like to thank Heinz Lang for his help in implementing the necessary extensions to eWRT and providing the ontology visualizations and Syed Kamran Ali Ahmad for proofreading the manuscript  ... 
doi:10.1109/dexa.2010.53 dblp:conf/dexaw/WeichselbraunWS10 fatcat:xo3lhntxundapgbfnfwittunlm

Pinterest Board Recommendation for Twitter Users

Xitong Yang, Yuncheng Li, Jiebo Luo
2015 Proceedings of the 23rd ACM international conference on Multimedia - MM '15  
In order to associate contents from the two social media platforms, we propose to use MultiLabel classification to map Twitter user followees to pinboard topics and visual diversification to recommend  ...  This paper proposes a novel pinboard recommendation system for Twitter users.  ...  For example, in [10] , Yan et al. proposed to identify the best Twitter accounts to promote YouTube videos, by mining the associations between topics learning from user tweets and their favorite YouTube  ... 
doi:10.1145/2733373.2806375 dblp:conf/mm/YangLL15 fatcat:i4xmaqpdqnczjapnxoafll7yva

Towards the Integration of Agricultural Data from Heterogeneous Sources: Perspectives for the French Agricultural Context Using Semantic Technologies [chapter]

Shufan Jiang, Rafael Angarita, Raja Chiky, Stéphane Cormier, Francis Rousseaux
2020 Lecture Notes in Business Information Processing  
These data coming from different types of IoT devices can also be combined with relevant information published in online social networks and on the Web in the form of textual documents.  ...  Semantic technologies and linked data provide a possibility for data integration and for automatic information extraction.  ...  We plan in a first phase build an ontology from twitter data that contains vocabulary in the existing thesaurus.  ... 
doi:10.1007/978-3-030-49165-9_8 fatcat:ejtamsf54rcmxoygrbwd5b6x7q

Ontology-based Approach for Identifying the Credibility Domain in Social Big Data [article]

Pornpit Wongthontham, Bilal Abu-Salih
2018 arXiv   pre-print
We experiment and evaluate our proposed approach with a public dataset collected from Twitter and from the politics domain.  ...  A challenge of managing and extracting useful knowledge from social media data sources has attracted much attention from academic and industry.  ...  Ontology is an explicit specification of a conceptualisation (Gruber, 1993) . The specification is the representation of the conceptualisations in a concrete form (Stevens, 2001) .  ... 
arXiv:1801.01624v2 fatcat:h74phmtnu5gzhkqjial5urqmrq

Building a Custom Sentiment Analysis Tool based on an Ontology for Twitter Posts

K. Vithiya Ruba, D. Venkatesan
2015 Indian Journal of Science and Technology  
Twitter is a popular micro-blogging platform which allows the users to share their opinion on any domain.  ...  The sentiment analysis done without feature extraction fails to give the deep result about the users opinion but in our proposed approach , features of the domain are extracted by building ontology which  ...  Data cleaning is nothing but the preprocessing of data which is done to reduce the noisy data, the following items should be removed from the retrieved tweets which will not be fit into the sentiment phase  ... 
doi:10.17485/ijst/2015/v8i13/61464 fatcat:2oo2fqx3erdfzfd62h4pxb6rxa

Ontology-based sentiment analysis of twitter posts

Efstratios Kontopoulos, Christos Berberidis, Theologos Dergiades, Nick Bassiliades
2013 Expert systems with applications  
This paper proposes the deployment of original ontology-based techniques towards a more efficient sentiment analysis of Twitter posts.  ...  Consequently, micro-blogging web sites have since become rich data sources for opinion mining and sentiment analysis.  ...  '' of the Ministry of Education, Lifelong Learning and Religious affairs and is funded by the European Commission (European Social Fund -ESF) and from national resources.  ... 
doi:10.1016/j.eswa.2013.01.001 fatcat:rutjtmipzjdp3j2uhgzwiwbyju

Spam, a Digital Pollution and Ways to Eradicate It

2019 International Journal of Engineering and Advanced Technology  
Spammers on Twitter seem to be more dangerous than the mail spammers as they exploit the limitation on the characters of Twitter for their own purposes.  ...  Due to the growing popularity of the microblogging and networking sites like twitter, Gmail, Facebook etc., there has been an increase in the number of spammers.  ...  The dataset used was raw and unstructured data from the date 05-2013 to 08-2013. They found these tweets from an online archive. They prepared the data to be tested from this raw data by themselves.  ... 
doi:10.35940/ijeat.b4107.129219 fatcat:uze7gfg3wrgjdmetvpuhzhl7p4

Text Mining for Personal Health Information on Twitter

Marina Sokolova, Yasser Jafer, David Schramm
2012 2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology  
One method uses WordNet as a source of health-related knowledge, another -an ontology of personal relations. We use Twitter data to empirically evaluate our methods.  ...  We also apply Machine Learning to demonstrate advantages of our extraction procedure when tweets containing PHI have to be automatically identified among other tweets.  ...  We worked with the Twitter data from the Content analysis of Web 2.0 workshop 2 . The data was organized as threads, i.e. consecutive tweets posted by users.  ... 
doi:10.1109/hisb.2012.37 dblp:conf/hisb/SokolovaJS12 fatcat:hbmhoxfcrfbeth5kotdnvvtioq
« Previous Showing results 1 — 15 out of 9,397 results