199,846 Hits in 6.7 sec

Building a Question-Answering Corpus Using Social Media and News Articles [chapter]

Paulo Cavalin, Flavio Figueiredo, Maíra de Bayser, Luis Moyano, Heloisa Candello, Ana Appel, Renan Souza
2016 Lecture Notes in Computer Science  
Moreover, to effectively provide rankings of answers to questions, we employ novel word vector based similarity measures between short sentences (that accounts for both questions and Tweets).  ...  We validated our methods on a recently released dataset of similarity between short Portuguese sentences.  ...  We combine the use of social media data together with novel, word vector based [4] , short-sentence similarity measures to create a QA-Corpus that can answer user question in free text form.  ... 
doi:10.1007/978-3-319-41552-9_36 fatcat:gxo3airbnndmfc3zgaii4ezwga

Text Analytics in Social Media [chapter]

Xia Hu, Huan Liu
2012 Mining Text Data  
We next discuss the research progress of applying text analytics in social media from different perspectives, and show how to improve existing approaches to text representation in social media, using real-world  ...  In this chapter, we first introduce the background of traditional text analytics and the distinct aspects of textual data in social media.  ...  vectors); while the methods for text in social media measures document similarity based on connectivity (e.g. the number of possible paths between authors of the documents) and structural similarity (  ... 
doi:10.1007/978-1-4614-3223-4_12 fatcat:ynmfabrhpjf6vils663o3rs2za

Classifying Short Text in Social Media: Twitter as Case Study

Faris Kateb, Jugal Kalita
2015 International Journal of Computer Applications  
Another challenge that researchers face is stream data, which refers to the huge and dynamic flow of text generated continuously from social media.  ...  With the huge growth of social media, especially with 500 million Twitter messages being posted per day, analyzing these messages has caught intense interest of researchers.  ...  They measure the similarity between a tweet t and news article s with T F -IDF score. Compare two short texts.  ... 
doi:10.5120/19563-1321 fatcat:dzus5l7hhnf7hhtkuvckyxivs4

Amharic Text Summarization for News Items Posted on Social Media

Abaynew Guadie, Debela Tesfaye, Teferi Kebebew
2021 International Journal of Intelligent Information Systems  
This paper introduces Amharic Text Summarization for News Items posted on social media, to summarize the news items posted Amharic texts over a time posted documents from social media on Twitter and Facebook  ...  For this the evaluation system shown that a very good results to summaries the posted texts on social media.  ...  Acknowledgements I would like to thank our Advisors and families for their given comments, and also those who helped us during this research study.  ... 
doi:10.11648/j.ijiis.20211006.14 fatcat:fwsrvepqnnav7iwq6yffcr6ntm

An Overview of Topic Discovery in Twitter Communication through Social Media Analytics

Andrey Chinnov, Pascal Kerschke, Christian Meske, Stefan Stieglitz, Heike Trautmann
2015 Americas Conference on Information Systems  
Therefore, this paper provides an overview of these challenges, matching methods and their expected usefulness for social media analytics.  ...  However, conventional topic discovery methods, which are widely used in large text corpora, face several challenges when they are applied in social media and particularly in Twitterthe most popular microblogging  ...  Due to the lack of specific approaches for topic discovery in short texts, some researchers applied conventional methods (or slight modifications) for the short text analysis (Ramage et al., 2010; Wang  ... 
dblp:conf/amcis/ChinnovKMST15 fatcat:stxgjlcvvfbg3nwrtvz53zsg54

Reliable Event Detection via Multiple Edge Computing on Streaming Traffic Social Data

Yipeng Ji, Jingyi Wang, Yan Niu, Hongyuan Ma
2021 IEEE Access  
Since a social traffic event is often described by multiple social media texts, it is significant to perform traffic event detection on streaming social media texts.  ...  ) and proceed to calculate event similarity between social media texts through meta-path weights.  ...  Based on the traffic event-based HIN, we propose the event similarity to measure the relationships between social media texts based on the weights of metapaths.  ... 
doi:10.1109/access.2021.3060624 fatcat:5finlsbexjam7jw6cy4rkbb6zy

Media Appropriateness

1993 Human Communication Research  
Finally, there was very little evidence of social infonnafwn processing influence on appropriateness, except for organizational newwmm' mtings of the newest medium, desktop video.  ...  This study assesses a scale measuring appropriateness of media for a variety oforganizational communication activities and then compmes seven media a m s s six organizational sites.  ...  For more details and other analyses from these sites, see R&Dl: Fish, Kraut, Root, and Rice (1993); GOVT: Rice and Contractor (1990) , Rice, Grant, Schmitz, and Torobin (1990) , Rice et al. (1992)  ... 
doi:10.1111/j.1468-2958.1993.tb00309.x fatcat:6cmoh7yolbavleqkis33cxxnrq

A Perspective on Text Classification, Clustering, and Named-entity Recognition in Social Media

Kia Jahanbin, Research Center for Social Determinants of Health, Jahrom Universityof Medical Sciences, Jahrom, Iran, Fereshte Rahmanian, Vahid Rahmanian, Masihollah Shakeri, Heshmatollah Shakeri, Zhila Rahmanian, Abdolreza Sotoodeh Jahromi
Mukkamala . (2014) and Nguyen . (2015) use interchangeably the terms Big Social Data and Social Big Data to refer the overall data created by social media.  ...  After the emergence of social media, an enormous amount of data started to generate.  ...  text, allocate the same topic forall words in one short text during Gibbs Sampling. it is a method developed by bibliometric research has a semantic similarity measure for documents that make use of citation  ... 
doi:10.21276/ambi.2019.06.1.ga01 fatcat:mvug2ixu5fe3jfshswi42lxofa

Survey on Popularity Prediction of Movies

Prof D. D. Gatade Nishigandha Aware, Sonali Mehetre, Anjali Khaire, Prathmesh Gunavat
2017 IJARCCE  
For that we use the data of social media like YouTube which contains large information about people's preferences.  ...  Now a day's online social media networking used in large amount to access information, share experiances, and express opinions.  ...  Vaidya for their time, suggestions, and for graciously agreeing to be on our committee, and always making themselves available. We cannot thank them enough.  ... 
doi:10.17148/ijarcce.2017.6453 fatcat:gq4yj5dz5nd4rd52vzpkhhvooy

Improving Semantic Relevance for Sequence-to-Sequence Learning of Chinese Social Media Text Summarization

Shuming Ma, Xu Sun, Jingjing Xu, Houfeng Wang, Wenjie Li, Qi Su
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
Current Chinese social media text summarization models are based on an encoderdecoder framework.  ...  In this work, our goal is to improve semantic relevance between source texts and summaries for Chinese social media summarization.  ...  However, it does not apply to Chinese social media text summarization, where texts are comparatively short and often full of noise.  ... 
doi:10.18653/v1/p17-2100 dblp:conf/acl/MaSXWLS17 fatcat:sngoadcjvfhfzjqmrp4gc54gai

Social Media Writing Style Fingerprint [article]

Himank Yadav, Juliang Li
2017 arXiv   pre-print
We present our approach for computer-aided social media text authorship attribution based on recent advances in short text authorship verification.  ...  We also considered writing bias in social media posts while collecting our training dataset to increase system robustness.  ...  As we can see, ensemble learning yielded better results for classifying short social media text messages.  ... 
arXiv:1712.04762v3 fatcat:si2yeivnhvgmzecp2bzbwkqtvy

Content Similarity Analysis of Written Comments under Posts in Social Media

Marzieh Mozafari, Reza Farahbakhsh, Noel Crespi
2019 2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS)  
Regarding short text mining, a number of recent efforts focus on using topic modeling methods such as LSA, NMF, and LDA [10] to find similarities between short texts in social media.  ...  Index Terms-Unrelated content, topic modeling, word embeddings, text similarity analysis, social media, Facebook feedback. I.  ... 
doi:10.1109/snams.2019.8931726 dblp:conf/snams/MozafariFC19 fatcat:grdsh4xqzzgyfas5abwl2hc2zq

Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media [article]

Xiang Dai and Sarvnaz Karimi and Ben Hachey and Cecile Paris
2020 arXiv   pre-print
Given the range of applications using social media text, and its unique language variety, we pretrain two models on tweets and forum text respectively, and empirically demonstrate the effectiveness of  ...  In addition, we investigate how similarity measures can be used to nominate in-domain pretraining data. We publicly release our pretrained models at  ...  Acknowledgments We would like to thank anonymous reviewers for their helpful comments. XD also thanks Shubin Du and Ying Zhou for early investigation of this work.  ... 
arXiv:2010.01150v1 fatcat:pgardw24qfgldpaw2gea5cq3cq

Analysis on an Auto Increment Detection System of Chinese Disaster Weibo Text

Hua Bai, Hualong Yu, Guang Yu, Alvaro Rocha, Xing Huang
2021 Journal of universal computer science (Online)  
Weibo is the most widely used Chinese social media tool.  ...  First, based on the deep learning- trained word vector model and a large-scale corpus, an unsupervised short-text feature representation method of disaster situation Weibo information is developed.  ...  Introduction initial corpus to generate a Word2vec semantic model for the short text representation of social media text during disasters.  ... 
doi:10.3897/jucs.65106 fatcat:bbluovthkjco3m3em6xbenhxzq

Exploring Social Context for Topic Identification in Short and Noisy Texts

Xin Wang, Ying Wang, Wanli Zuo, Guoyong Cai
to tackle short and noisy texts in social media, which result in a Sociological framework for Topic Identification (STI).  ...  With the pervasion of social media, topic identification in short texts attracts increasing attention in recent years.  ...  Acknowledgments We truly thank the anonymous reviewers for their pertinent comments. In addition, we truly thank the help of DMML at ASU.  ... 
doi:10.1609/aaai.v29i1.9463 fatcat:4fltru6ncjfohkct4gcm7iykta
« Previous Showing results 1 — 15 out of 199,846 results