184 Hits in 1.8 sec

The Information Content of Multiword #Hashtags

Zvi Ben-Ami, Tomer Geva, Inbal Yahav
2018 International Conference on Information Systems  
One such interesting phenomenon is the use of hashtags to emphasize important content. In this paper, we evaluate the information content of hashtags for sentiment analysis applications.  ...  We find that breaking down hashtags into multiple terms significantly improves the predictive accuracy of sentiment analysis procedures, and more generally, that hashtags are highly informative for sentiment  ...  The Information Content of Multiword #Hashtags Thirty Ninth International Conference on Information Systems, San Francisco 2018 2 To our knowledge, this work is the first to evaluate the information content  ... 
dblp:conf/icis/Ben-AmiGY18 fatcat:ivuqhyk3p5bbjhrf57dgfevbpy

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

Additional pre-procesing steps for handling multiword usernames and hashtags have also been incorporated in the proposed work.  ...  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.  ... 
doi:10.35940/ijitee.k1352.0981119 fatcat:a2wtfkvsqzdlng7tjfrx6tafja

Multimodal Sentiment Analysis of Social Media

Diana Maynard, David Dupplaw, Jonathon S. Hare
2013 SGAI Conferences  
The analysis of multimedia content complements this work in order to help resolve ambiguity and to provide further contextual information.  ...  We provide two main innovations in this work: first, the novel combination of text and multimedia opinion mining tools; and second, the adaptation of NLP tools for opinion mining specific to the problems  ...  Evaluation on the hard-to-recognise cases (non-camel-cased multiword hashtags) produced scores of 86.91% Precision, 90% Recall, and an F-measure of 88.43%.  ... 
dblp:conf/sgai/MaynardDH13 fatcat:bavps6e6szgmxhkuoz3xfjpbju

Entity-Based Opinion Mining from Text and Multimedia [chapter]

Diana Maynard, Jonathon Hare
2015 Studies in Computational Intelligence  
detected in this corpus, of which 408 were identified as multiword hashtags (we included combinations of letters and numbers as multiword, but not abbreviations). 281 were camelcased and/or combinations  ...  Evaluation on the hard-to-recognise cases (non-camel-cased multiword hashtags) produced scores of 86.91% Precision, 90% Recall, and an F-measure of 88.43%.  ... 
doi:10.1007/978-3-319-18458-6_4 fatcat:kydbtz5olfgrja5ozcjg5jkgcy

We usually don't like going to the dentist. Using common sense to detect irony on Twitter

Cynthia Van Hee, Els Lefever, Véronique Hoste
2018 Computational Linguistics  
We further investigate how such implicit sentiment information affects irony detection by assessing a state-of-the-art irony classifier before and after it is informed with implicit sentiment information  ...  In this article, we therefore address the challenge of modeling implicit or prototypical sentiment in the framework of automatic irony detection.  ...  is filled with #irony"), and misuse of the hashtags by adding it to non-ironic content.  ... 
doi:10.1162/coli_a_00337 fatcat:qza6yucc55ccbkfmccsmub7t2i

What kills us and what moves us: A comparative discourse analysis of heart disease and breast cancer

Claire E O'Hanlon
2019 Digital Health  
The #HeartDisease social media community is less engaged, and content is less specific to both the disease and individual experience than #BreastCancer.  ...  The #BreastCancer corpus uniquely included community-specific initialism hashtags.  ...  Acknowledgements: I would like to thank William Marcellino for his guidance, and Audun Utengen and the team at Symplur, Inc. for providing the Twitter data.  ... 
doi:10.1177/2055207619844865 pmid:31069103 pmcid:PMC6495432 fatcat:qkkynx5savedtlt7m3cp7aarla

#andràtuttobene: Images, Texts, Emojis and Geodata in a Sentiment Analysis Pipeline

Pierluigi Vitale, Serena Pelosi, Mariacristina Falco
2020 Italian Conference on Computational Linguistics  
The study is based on the analysis of all the posts published on Instagram under the hashtag #andràtuttobene on May 4, May 18 and June 3, 2020.  ...  The aim of this research is to provide a set of procedures revealing the different polarity trends for each kind of expression and to propose a single comprehensive measure.  ...  with the same information used to analyze verbal features.  ... 
dblp:conf/clic-it/VitalePF20 fatcat:bzjytbxob5abpiur7qoxm45ekm

Samskara Minimal structural features for detecting subjectivity and polarity in Italian tweets

Irene Russo, Monica Monachini
2016 Italian Conference on Computational Linguistics  
Sentiment analysis classification tasks strongly depend on the properties of the medium that is used to communicate opinionated content.  ...  There are some limitations in Twitter that force the user to exploit structural properties of this social network with features that have pragmatic and communicative functions.  ...  Secondly, different media and platforms impose different constraints on the structure of the content expressed.  ... 
dblp:conf/clic-it/RussoM16 fatcat:jhzfdkpuwfdd7afn42kc6i4fry

Gradiant-Analytics: Training Polarity Shifters with CRFs for Message Level Polarity Detection

Héctor Cerezo-Costas, Diego Celix-Salgado
2015 Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)  
The system combines the use of polarity dictionaries and Conditional Random Fields to obtain syntactic and semantic features, which are afterwards fed to a statistical classifier in order to obtain the  ...  To improve results, an ensemble of classifiers was employed by combining the individual outputs with majority voting strategy.  ...  To deal with the multiword problem of hashtags, we developed a module that uses CRFs with character-level features to find word terminations in hashtags.  ... 
doi:10.18653/v1/s15-2090 dblp:conf/semeval/Cerezo-CostasC15 fatcat:3atyettb3fh3pjonflu5xmrzqm

Minority Language Twitter: Part-of-Speech Tagging and Analysis of Irish Tweets

Teresa Lynn, Kevin Scannell, Eimear Maguire
2015 Proceedings of the Workshop on Noisy User-generated Text  
We also report on state-of-the-art tagging results of training and testing three existing POStaggers on our new dataset.  ...  We contribute to recent advances in this area of research by reporting on the development of part-ofspeech annotation scheme and annotated corpus for Irish language tweets.  ...  We choose to differentiate between N and VN to avoid losing this verbal information in what would otherwise be a regular prepositional phrase. • #MWE: Multiword hashtag These are hashtags containing strings  ... 
doi:10.18653/v1/w15-4301 dblp:conf/aclnut/LynnSM15 fatcat:6yslnxgmarep5olyrgpzki2ffe

Multi-task Pairwise Neural Ranking for Hashtag Segmentation

Mounica Maddela, Wei Xu, Daniel Preoţiuc-Pietro
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
However, the semantic content of hashtags is not straightforward to infer as these represent ad-hoc conventions which frequently include multiple words joined together and can include abbreviations and  ...  . 1 Our novel neural approaches demonstrate 24.6% error reduction in hashtag segmentation accuracy compared to the current state-of-the-art method.  ...  The views and conclusions contained in this publication are those of the authors and should not be interpreted as representing official policies or endorsements of the U.S. Government.  ... 
doi:10.18653/v1/p19-1242 dblp:conf/acl/MaddelaXP19 fatcat:u64clehp4jbjbnytkb47z2oxqa

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  
The setting includes specialised components for spelling correction of tweets as well as hashtag and username decoding.  ...  The tools which perform sufficiently well on electronic press, books and other type of non-interactive content may poorly handle noisy, colloquial and multilingual textual data which make the majority  ...  It was also partially financed as part of the in-vestment in the CLARIN-PL research infrastructure funded by the Polish Ministry of Science and Higher Education.  ... 
doi:10.18653/v1/w17-2215 dblp:conf/latech/OgrodniczukK17 fatcat:mibwyzvfkbay3g6gby5lfdx224

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)  
The novelty of the system is the employment of a topic modeling approach in order to adapt the semantic-affective space for each tweet.  ...  In addition, significant enhancements were made in the main system dealing with the data preprocessing and feature extraction including the employment of word embeddings.  ...  the BabyRobot project supported by the EU Horizon 2020 Programme, grant number: 687831.  ... 
doi:10.18653/v1/s16-1023 dblp:conf/semeval/PalogiannidiKCK16 fatcat:k6fk62sqvzcp5lo72qvrxvhg4e

Dependency-based Topic-Oriented Sentiment Analysis in Microposts

Prasadith Buddhitha, Diana Inkpen
2015 Symposium on Information Management and Big Data  
Our experiments are based on the data from the Semantic Evaluation Exercise 2015 (SemEval-2015), task 10, subtask C. The dependency parser that we used is adapted to this kind of text.  ...  detecting the correct attachment points for the polarity words.  ...  Microblogs have become one of the most popular and widely-used sources of information, where users share real-time information on many topics.  ... 
dblp:conf/simbig/BuddhithaI15 fatcat:6bekixsoljgbbmwau46mbsjbbi

Tweet Contextualization: a Strategy Based on Document Retrieval Using Query Enrichment and Automatic Summarization

Jorge Vivaldi, Iria da Cunha
2013 Conference and Labs of the Evaluation Forum  
In this research, we use words sequences that agree with the typical terminological patterns, name entities, hashtags and Twitter users accounts, since we consider that they are representative of tweets  ...  information related with different tweets, that is, a summary that explains a specific tweet.  ...  Acknowledgements This work has been partially financed by the Spanish projects RICOTERM 4 (FFI2010-21365-C03-01) and APLE 2 (FFI2012-37260), and a Juan de la Cierva grant (JCI-2011-09665).  ... 
dblp:conf/clef/VivaldiC13 fatcat:keeos2dyfbeczixhiipa7jbcy4
« Previous Showing results 1 — 15 out of 184 results