291 Hits in 3.9 sec

Citius: A Naive-Bayes Strategy for Sentiment Analysis on English Tweets

Pablo Gamallo, Marcos Garcia
2014 Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)  
When the classifier is provided with a polarity lexicon and multiwords it achieves 63% F-score.  ...  In addition, in order to detect tweets with and without polarity, the system makes use of a very basic rule that searchs for polarity words within the analysed tweets/texts.  ...  1, 520, positive and negative lemmas. • Hedonometer 3 contains about 10, 000 frequent words extracted from tweets which were classified as expressing some degree of hapiness (Dodds et al., 2011) .  ... 
doi:10.3115/v1/s14-2026 dblp:conf/semeval/GamalloG14 fatcat:76bwuxtgwnh5pj5jgcnclll4zu

An Effective Knowledge-Based Pre-processing System with Emojis and Emoticons Handling on Twitter and Google+

New dictionaries have been compiled to provide a language to the emotional contents carried by emojis and emoticons.  ...  Additional pre-procesing steps for handling multiword usernames and hashtags have also been incorporated in the proposed work.  ...  It links Unicode of emojis with their English language meanings extracted from four different web resources and integrates these resources with BabelNet to infer sense definitions.  ... 
doi:10.35940/ijitee.k1352.0981119 fatcat:a2wtfkvsqzdlng7tjfrx6tafja

NET-LDA: a novel topic modeling method based on semantic document similarity

2020 Turkish Journal of Electrical Engineering and Computer Sciences  
Two datasets in the English and Turkish languages and 12 different domains have been evaluated to show the independence of the model from both language and domain.  ...  It builds a document as a mixture of topics and a topic is modeled as a probability distribution over words.  ...  (iii) Contrary to the existing LDA models, in the NET-LDA, multiword aspects, as well as word aspects, are extracted from documents. (iv) The NET-LDA model is language-independent.  ... 
doi:10.3906/elk-1912-62 fatcat:wx62lg46yfarpj5wik7mdpkiae

Tweester at SemEval-2016 Task 4: Sentiment Analysis in Twitter Using Semantic-Affective Model Adaptation

Elisavet Palogiannidi, Athanasia Kolovou, Fenia Christopoulou, Filippos Kokkinos, Elias Iosif, Nikolaos Malandrakis, Haris Papageorgiou, Shrikanth Narayanan, Alexandros Potamianos
2016 Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)  
Our system comprises of multiple independent models such as neural networks, semantic-affective models and topic modeling that are combined in a probabilistic way.  ...  In addition, significant enhancements were made in the main system dealing with the data preprocessing and feature extraction including the employment of word embeddings.  ...  Acknowledgements: Elisavet Palogiannidi, Elias Iosif and Alexandros Potamianos were partially funded by the SpeDial project supported by the EU Seventh Framework Programme (FP7), grant number 611396 and  ... 
doi:10.18653/v1/s16-1023 dblp:conf/semeval/PalogiannidiKCK16 fatcat:k6fk62sqvzcp5lo72qvrxvhg4e

Identifying Potential Adverse Drug Events in Tweets Using Bootstrapped Lexicons

Eric Benzschawel
2016 Proceedings of the ACL 2016 Student Research Workshop  
This method was able to identify misspellings, slang terms, and other non-standard language features of social media data to drive a competitive ADE detection system.  ...  Adverse drug events (ADEs) are medical complications co-occurring with a period of drug usage. Identification of ADEs is a primary way of evaluating available quality of care.  ...  Nianwen Xue, the advisor for this work, which presents a portion of a masters thesis on the same topic titled Identifying Adverse Drug Events in Twitter Data Using Semi-Supervised Bootstrapped Lexicons  ... 
doi:10.18653/v1/p16-3003 dblp:conf/acl/Benzschawel16 fatcat:p5kkieioczbqxf63wpk6fny474

Wikipedia based semantic smoothing for twitter sentiment classification

Dilara Torunoglu, Gurkan Telseren, Ozgun Sagturk, Murat C. Ganiz
2013 2013 IEEE INISTA  
Results of the extensive experiments show that our approach improves the performance of NB and even can exceed the accuracy of SVM on Twitter Sentiment 140 dataset.  ...  NB having several advantages on Jower complexity and simpler training procedure, it suffers from zero probability problems (Rish, 2001) .  ...  We are motivated by this study and adopted same topic signature mapping approach however instead of using multiword phrases that are extracted from documents we employ Wikipedia articles, categories and  ... 
doi:10.1109/inista.2013.6577649 fatcat:jvyyfalhojag5g7ybdql7mqtde

La desigualdad de género en Twitter durante las elecciones británicas de 2019

Carla Fernández Melendres, Aroa Orrequia Barea
2021 Quaderns de Filologia: Estudis Lingüístics  
Actualmente, las plataformas de redes sociales como Twitter tienen un papel esencial en la política y los movimientos sociales.  ...  El objetivo de este artículo es comparar y contrastar el lenguaje utilizado en Twitter para referirse a los candidatos de las últimas elecciones generales del Reino Unido de diciembre de 2019 para crear  ...  Keywords extracted from Johnson's and Corbyn's subcorpora are related to their attitude towards politics and to their policies.  ... 
doi:10.7203/qf.0.21982 fatcat:vcr6b2j2bzeo5ha4pawwwnyqoy

Novel Semantics-based Distributed Representations for Message Polarity Classification using Deep Convolutional Neural Networks

Abhinay Pandya, Mourad Oussalah
2017 Proceedings of the 9th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management  
) are sentiment encoded distributed representations of multi-word expressions (MWEs); Sense-Disambiguated Word Embeddings(SDWE) are sense-specific distributed representations of words; and WordNet embeddings  ...  In this paper, we propose three semantics-based distributed representations of words and phrases as features for message polarity classification: Sentiment-Specific Multi-Word Expressions Embeddings(SSMWE  ...  ACKNOWLEDGEMENTS We would like to thank the anonymous reviewers for their valuable suggestions because of which the technical quality of the work presented in this paper has improved.  ... 
doi:10.5220/0006500800710082 dblp:conf/ic3k/PandyaO17 fatcat:kx3t2cb32rg5tite6joaziknbm

Sentiment Analysis of Hotel Review

Dhore Akshada Sharad, Dixit Shraddha Ashok, Dixit Pratik Dattatray
2018 IJARCCE  
Sentiment analysis is the automated process of understanding and opinion about a given subject from return or written language.  ...  Millions of the peoples express their views on social media. This huge data will beneficial for better product marketing.  ...  They check how the social, political, cultural and economic sphere produces an effect on public mood expressed on Twitter.  ... 
doi:10.17148/ijarcce.2018.71139 fatcat:lkk3nbsmvrechgavhwp4b5q4o4

VMWE discovery: a comparative analysis between Literature and Twitter Corpora

Vivian Stamou, Artemis Xylogianni, Marilena Malli, Penny Takorou, Stella Markantonatou
2020 Zenodo  
We evaluate manually five lexical association measurements as regards the discovery of Modern Greek verb multiword expressions with two or more lexicalised components using mwetoolkit3 (Ramisch et al.,  ...  The results of LL, MLE and T-score were found to overlap significantly in both the fiction and the Twitter corpora, while the results of PMI and Dice do not.  ...  Acknowledgements This work was supported by the project "GRE-Taste" (T1EDK-02015) that is funded by the action "RESEARCH-CREATE-INNOVATE" and co-financed by Greek National Funds and the European Union.  ... 
doi:10.5281/zenodo.6619433 fatcat:6glveritwvf2dk5dv3yrxmehoe

Lexical Correction of Polish Twitter Political Data

Maciej Ogrodniczuk, Mateusz Kopeć
2017 Proceedings of the Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature  
This paper aims at investigating how Polish Twitter data (in a slightly controlled 'political' flavour) differs from expectation of linguistic tools and how it could be corrected to be ready for processing  ...  The setting includes specialised components for spelling correction of tweets as well as hashtag and username decoding.  ...  by the European Commission from the FP7 programme (grant agreement number 287863) and from the Polish Ministry of Science support programme (grant agreement number 3177/7.PR/2014/2).  ... 
doi:10.18653/v1/w17-2215 dblp:conf/latech/OgrodniczukK17 fatcat:mibwyzvfkbay3g6gby5lfdx224

Using Multi-View Learning to Improve Detection of Investor Sentiments on Twitter

Zvi Ben-Ami, Ronen Feldman, Binyamin Rosenfeld
2014 Journal of Computacion y Sistemas  
With this, we can expand the coverage of generic SA tools and learn new sentiment expressions.  ...  On the other hand, stock-related messages primarily refer to the state of specific entities -companies and their stocks, at specific times (of sending).  ...  This work is supported by the Israel Ministry of Science and Technology Center of Knowledge in Machine Learning and Artificial Intelligence and the Israel Ministry of Defense.  ... 
doi:10.13053/cys-18-3-2019 fatcat:eyqbqyvadnfvnmqxclkmcfeka4

A Unified Framework to Identify and Extract Uncertainty Cues, Holders, and Scopes in One Fell-Swoop [chapter]

Rania Al-Sabbagh, Roxana Girju, Jana Diesner
2015 Lecture Notes in Computer Science  
Like in many other languages, Arabic UCs can be either unigrams or multiword expressions.  ...  for all uncertainty-related tasks consumes more time for feature extraction and deprives tasks from informing one another.  ... 
doi:10.1007/978-3-319-18111-0_24 fatcat:a6l5ebmhnvdcvitnhiuxe6o6ju

Designation of Situation Model in Twitter using Maximal Frequent Sequences

Anna Atyagina, Yulia Ledeneva, René Arnulfo García-Hernández
2015 Research in Computing Science  
Hashtag is definitely one of the most significant features of Twitter which now is spread all over the social networking services.  ...  Also this method can be used for analysis of hashtag combinations and reconstruction of concepts based on the results of 1-grams and 2-grams, as we presented in detailed example of analysis of the following  ...  Work done under partial support of Mexican Government (CONACyT, SNI, UAEM). The authors thank Autonomous University of the State of Mexico for their assistance.  ... 
doi:10.13053/rcs-95-1-10 fatcat:3c4aiof3bbh3diemqxvohq6gfa

A Dependency Parser for Tweets

Lingpeng Kong, Nathan Schneider, Swabha Swayamdipta, Archna Bhatia, Chris Dyer, Noah A. Smith
2014 Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)  
Our experiments show that the parser achieves over 80% unlabeled attachment accuracy on our new, high-quality test set and measure the benefit of our contributions.  ...  The parser builds on several contributions: new syntactic annotations for a corpus of tweets (TWEEBANK), with conventions informed by the domain; adaptations to a statistical parsing algorithm; and a new  ...  Acknowledgments The authors thank the anonymous reviewers and André  ... 
doi:10.3115/v1/d14-1108 dblp:conf/emnlp/KongSSBDS14 fatcat:rgp3dfo4sbctpgzc2aohbe3f4a
« Previous Showing results 1 — 15 out of 291 results