272 Hits in 3.6 sec

Text normalization for named entity recognition in Vietnamese tweets

Vu H. Nguyen, Hien T. Nguyen, Vaclav Snasel
2016 Computational Social Networks  
[53] used entity-linking-based features, and other researchers used CRFs.  ...  capital letters; and (3) a model for training and recognizing named entities in Vietnamese tweets.  ... 
doi:10.1186/s40649-016-0032-0 pmid:29355207 pmcid:PMC5749168 fatcat:4q7vx6vhhfdo3ddw4izsdgo2gy

TweetNLP: Cutting-Edge Natural Language Processing for Social Media [article]

Jose Camacho-Collados and Kiamehr Rezaee and Talayeh Riahi and Asahi Ushio and Daniel Loureiro and Dimosthenis Antypas and Joanne Boisson and Luis Espinosa-Anke and Fangyu Liu and Eugenio Martínez-Cámara and Gonzalo Medina and Thomas Buhrmann and Leonardo Neves and Francesco Barbieri
2022 arXiv   pre-print
TweetNLP supports a diverse set of NLP tasks, including generic focus areas such as sentiment analysis and named entity recognition, as well as social media-specific tasks such as emoji prediction and  ...  In this paper we present TweetNLP, an integrated platform for Natural Language Processing (NLP) in social media.  ...  ., the Cardiff University Innovation for All scheme and the R&D&I grant PID2020-116118GA-I00 funded by MCIN/AEI/10.13039/501100011033 for partially funding this project.  ... 
arXiv:2206.14774v2 fatcat:6wo2umxow5f73jlz4xuzmaakc4

Critical Questions About Scientific Research Publications in the Online Mask Debate [chapter]

Jean Goodwin, Ekaterina Bogomoletc
2022 Argumentation Library  
These results indicate specific areas for interventions to improve reasoning about research publications.  ...  In this study, we explore the nature and extent of the public's abilities to assess research publications through analyzing a corpus of close to 5 K tweets from the early months of the pandemic which mentioned  ...  We would also like to thank Altmetric (Digital Science), for providing us with access to the Altmetric Explorer tool for data collection.  ... 
doi:10.1007/978-3-030-91017-4_17 fatcat:i5nbmsnp3jfa3hvjtnbbs33bve

Visualization of Arabic Entities in Online Social Media using Machine Learning

Khowla Mohammed Alyamani, Abdul Khader
2021 International Journal of Advanced Computer Science and Applications  
Finally, the entity is passed to a gazetteer model which searches for the entity in three gazetteers (person, location, and organization), and accordingly determines the number of times the entity reference  ...  The experimental results show that accuracy of the developed model in classifying the tweets is nearly 90%.  ...  The authors in [2] built a Malayalam NER classifier and in [17] for Vietnamese by using a neural network.  ... 
doi:10.14569/ijacsa.2021.0120148 fatcat:6d2i4lmpmzdonovhqqeutalxiy

Crisis in a Foreign Language: Emergency Services and Limited English Populations

Amirah M. Majid, Emma S. Spiro
2016 International Conference on Information Systems for Crisis Response and Management  
We discuss the practical implications of these results, and offer directions for future work and improvement of practices.  ...  As such, it is important to understand how these new technologies offer opportunities and barriers to information access for population affected during crisis events.  ...  We would also like to thank the reviewers for their thoughtful comments.  ... 
dblp:conf/iscram/MajidS16 fatcat:gpowgpvsk5dclnyu35iqyftf5a

TweetNorm: Text Normalization on Italian Twitter Data

Daniel Weber, Desislava Zhekova
2016 Conference on Natural Language Processing  
The paper shows that with a set of fixed language-independent rules and trained rules for language-dependent abbreviation and acronym expansion good results can be achieved for normalizing Italian Twitter  ...  We present TweetNorm 1 , a system which normalizes Italian tweets in a way that the amount of microblog slang and distorted text appearance is drastically reduced and the normalized output has a much cleaner  ...  Moreover, while good POS taggers for tweets are available for English, this is not the case for Italian.  ... 
dblp:conf/konvens/WeberZ16 fatcat:im5g5duc3zgqta4d5zrxpvsgf4

Risk Communication in Asian Countries: COVID-19 Discourse on Twitter [article]

Sungkyu Park, Sungwon Han, Jeongwook Kim, Mir Majid Molaie, Hoang Dieu Vu, Karandeep Singh, Jiyoung Han, Wonjae Lee, Meeyoung Cha
2020 arXiv   pre-print
For dynamics, we find an inverse relationship between the tweet count and topical diversity.  ...  This finding calls for a need to analyze the public discourse by new measures, such as topical dynamics.  ...  We have set up two keywords, "Corona" and "Wuhan pneumonia" to crawl tweets (see Table 1 to find exact keywords used for crawling tweets for each country) and collected tweets for the three months from  ... 
arXiv:2006.12218v3 fatcat:smfhooenira7rfcppjm3xmwed4

Editorial of the evolving and hybrid systems' modelling special issue

Lazaros Iliadis, Ilias Maglogiannis
2020 Evolving Systems  
The link with the Multicriteria Technique for Order of Preference by Similarity to Ideal Solution has been investigated. O. Ekaba Bisong and B.  ...  on determining which tweets are causing multiple sentiment polarity alternations to occur, based on a window segmentation approach.  ... 
doi:10.1007/s12530-020-09353-2 fatcat:4r4qcsx7obejpjlmli5m3xd5ae

Social media and crisis management: CERC, search strategies, and Twitter content

Kenneth A. Lachlan, Patric R. Spence, Xialing Lin, Kristy Najarian, Maria Del Greco
2016 Computers in Human Behavior  
The findings are discussed in terms of the Crisis and Emergency Risk Communication (CERC) model of crisis management and implications for emergency management agencies.  ...  A multi-level content analysis of tweets collected in the lead up to landfall suggests that emergency management agencies largely underutilized the medium, and that actionable information was easier to  ...  search term in question; these exact replications contain live links and links to user profiles, and can be saved as .html files for further examination.  ... 
doi:10.1016/j.chb.2015.05.027 fatcat:4z6w7wwtlvfzvflnx2japo65yi

Twitter Big Data as a Resource for Exoskeleton Research: A Large-Scale Dataset of about 140,000 Tweets and 100 Research Questions [article]

Nirmalya Thakur
2022 arXiv   pre-print
First, it presents an open-access dataset of about 140,000 tweets about exoskeletons that were posted in a 5-year period from May 21, 2017, to May 21, 2022.  ...  The Internet of Everything style of today's living, characterized by people spending more time on the internet than ever before, with a specific focus on social media platforms, holds the potential for  ...  the first 20,000 tweets.  ... 
arXiv:2111.04476v4 fatcat:tnvjypclzjgivohdlpwwuqcpwm

A Review on Event-Based Epidemic Surveillance Systems that Support the Arabic Language

Meshrif Alruily
2018 International Journal of Advanced Computer Science and Applications  
In other words, no existing event-based system in the literature has yet been developed specifically for Arabic health news reports to monitor epidemic diseases.  ...  With the revolution of the internet, many eventbased systems have been developed for monitoring epidemic threats. These systems rely on unstructured data gathered from various online sources.  ...  Nguyen and Nguyen [46] , [60] developed the Disease Extraction System for Real-time Monitoring (DESRM). This system is used for Vietnamese online news.  ... 
doi:10.14569/ijacsa.2018.0911102 fatcat:27locxlyfzhjtcr6e2samnpkmq

Situational Awareness for Low Resource Languages: the LORELEI Situation Frame Annotation Task

Stephanie M. Strassel, Ann Bies, Jennifer Tracey
2017 European Conference on Information Retrieval  
Data is by definition relatively scarce for these languages, and real operational data may be impossible to come by, necessitating the use of "proxy" data sources.  ...  Rather than evaluating these capabilities in English, LORELEI is particularly concerned with advancing human language technology performance for low resource languages.  ...  In 2017 the NER task will be replaced by an evaluation of Entity Discovery and Linking (EDL).  ... 
dblp:conf/ecir/StrasselBT17 fatcat:fdybfyfgijfljci7fiu7s4sbvi

Race and Resistance Amid Feminism, Priming, and Capitalism: The (surprisingly-globalized) Visual of an Asian American Woman Activist

Jenny Korn
2018 Ada: A Journal of Gender, New Media, and Technology  
Dao was also reported initially as Chinese, instead of Vietnamese.  ...  As tweets use hashtags to connect to a larger conversation held online(Korn 2013(Korn , 2015a)), posters that employ hashtags represent tweets materially; posters made out of paper are held above or in  ... 
doi:10.5399/uo/ada.2018.14.8 fatcat:tqzlnuo7lzhodj5tlkkvlqphfa

Annotation Curricula to Implicitly Train Non-Expert Annotators

Ji-Ung Lee, Jan-Christoph Klie, Iryna Gurevych
2022 Computational Linguistics  
Finally, we provide a proof of concept for annotation curricula in a carefully designed user study with 40 voluntary participants who are asked to identify the most fitting misconception for English tweets  ...  To do so, this work formalizes annotation curricula for sentence- and paragraph-level annotation tasks, defines an ordering strategy, and identifies well-performing heuristics and interactively trained  ...  We thank Michael Bugert, Richard Eckart de Castilho, Max Glockner, Ulf Hamster, Yevgeniy Puzikov, Kevin Stowe, and the anonymous reviewers for their thoughtful comments and feedback, as well as all anonymous  ... 
doi:10.1162/coli_a_00436 fatcat:kapu2oz2n5erplirhhulryxkgy


Huyen Trang Phan, Ngoc Thanh Nguyen, Dosam Hwang
2021 Journal of Computer Science and Cybernetics  
Additionally, we discuss the challenges and possible research directions for future research in this field.  ...  This survey presents a summary of the necessary stages for building a complete model to be used in sentiment analysis.  ...  This lexicon provides the sentiment strength, either positive or negative, for each opinion. Then, the average scores of sentiment strengths are calculated for each entity.  ... 
doi:10.15625/1813-9663/37/4/15892 fatcat:2dgv3sygovgelk3mffmvnmokay
« Previous Showing results 1 — 15 out of 272 results