Filters








4,952 Hits in 2.5 sec

Using Word Embeddings in Twitter Election Classification [article]

Xiao Yang, Craig Macdonald, Iadh Ounis
2017 arXiv   pre-print
In this paper, using a Twitter election classification task that aims to detect election-related tweets, we investigate the impact of the background dataset used to train the embedding models, the context  ...  Word embeddings and convolutional neural networks (CNN) have attracted extensive attention in various classification tasks for Twitter, e.g. sentiment classification.  ...  In this paper, using a dataset of tweets collected during the Venezuela parliamentary election in 2015, we investigate the use of word embeddings with CNN in a new classification task, which aims to identify  ... 
arXiv:1606.07006v3 fatcat:lzypzdmtvzhrfgkvmirrhebfku

Using word embeddings in Twitter election classification

Xiao Yang, Craig Macdonald, Iadh Ounis
2017 Information retrieval (Boston)  
In this paper, using a Twitter election classification task that aims to detect election-related tweets, we investigate the impact of the background dataset used to train the embedding models, the context  ...  Word embeddings and convolutional neural networks (CNN) have attracted extensive attention in various classification tasks for Twitter, e.g. sentiment classification.  ...  In this paper, using a dataset of tweets collected during the Venezuela parliamentary election in 2015, we investigate the use of word embeddings with CNN in a new classification task, which aims to identify  ... 
doi:10.1007/s10791-017-9319-5 fatcat:tpvqnkhx4jd3xepaz6djznkkhq

Transfer Learning for Multi-language Twitter Election Classification

Xiao Yang, Richard McCreadie, Craig Macdonald, Iadh Ounis
2017 Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017 - ASONAM '17  
We generalise the learned classifier models for cross-language classification by using a linear translation approach to map the word embedding vectors from one language into another.  ...  We combine transfer learning with different classifiers such as Support Vector Machines (SVM) and state-of-the-art Convolutional Neural Networks (CNN), which make use of word embedding representations  ...  The authors would like to thank the assessors for their efforts in reviewing tweets.  ... 
doi:10.1145/3110025.3110059 dblp:conf/asunam/YangMMO17 fatcat:sjsvdj7yofcn3mpklvmilzdlai

On the Reproducibility and Generalisation of the Linear Transformation of Word Embeddings [chapter]

Xiao Yang, Iadh Ounis, Richard McCreadie, Craig Macdonald, Anjie Fang
2018 Lecture Notes in Computer Science  
In addition, we also provide best practices when using linear transformation for multi-language Twitter election classification.  ...  Following the verification of previous findings, we then study the generalisation of linear transformation in a multi-language Twitter election classification task.  ...  The authors would like to thank the assessors for their efforts in reviewing tweets.  ... 
doi:10.1007/978-3-319-76941-7_20 fatcat:v5wxeokntvc6ncsl4vpuyzjo5y

Detecting Social Media Manipulation in Low-Resource Languages [article]

Samar Haider, Luca Luceri, Ashok Deb, Adam Badawy, Nanyun Peng, Emilio Ferrara
2020 arXiv   pre-print
We discovered that a high number of accounts posting in Tagalog were suspended as part of Twitter's crackdown on interference operations after the 2016 US Presidential election.  ...  By combining text embedding and transfer learning, our framework can detect, with promising accuracy, malicious users posting in Tagalog without any prior knowledge or training on malicious content in  ...  To learn word embeddings and train classification models, we use the FastText 3 framework.  ... 
arXiv:2011.05367v1 fatcat:vxqo2b5bijgvllzygv7vpwuxsq

Building Type Classification from Social Media Texts via Geo-Spatial Textmining

Matthias Haberle, Martin Werner, Xiao Xiang Zhu
2019 IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium  
In this work, we present a model for building type classification from Twitter text messages (tweets) by employing geospatial text mining methods.  ...  First, we apply standard text pre-processing methods and convert the tweets into sentence vectors using fastText.  ...  For example Twitter text messages have been used to produce word embeddings and to predict whether a tweet is related to the Venezuela parliamentary election in 2015 and the Philippines general election  ... 
doi:10.1109/igarss.2019.8898836 dblp:conf/igarss/Haberle0Z19 fatcat:dfvfnpasi5ejlh2xhilgeh56ym

Combining Post Sentiments and User Participation for Extracting Public Stances from Twitter

Jenq-Haur Wang, Ting-Wei Liu, Xiong Luo
2020 Applied Sciences  
Since social media posts are usually very short, word embedding models are first used to learn different word usages in various contexts.  ...  To better understand what the public think about a topic, sentiment classification techniques have been widely used to estimate the overall orientation of opinions in post contents.  ...  The Effects of Word Embedding Models on Sentiment Classification In this section, we tested the performance of sentiment classification using LSTM for different word embedding models on various datasets  ... 
doi:10.3390/app10228035 fatcat:lyjjpg5bg5bhhoolhdiiy2md2i

Political discourse classification in social networks using context sensitive convolutional neural networks

Aritz Bilbao-Jayo, Aitor Almeida
2018 Proceedings of the Sixth International Workshop on Natural Language Processing for Social Media  
In this study we propose a new approach to analyse the political discourse in online social networks such as Twitter.  ...  Using this taxonomy, we have validated our approach analysing the Twitter activity of the main Spanish political parties during 2015 and 2016 Spanish general election and providing a study of their discourse  ...  CSO2015-64495-R (Electronic Regional Manifestos Project); and NVIDIA Corporation with the donation of the Titan X used for this research.  ... 
doi:10.18653/v1/w18-3513 dblp:conf/acl-socialnlp/Bilbao-JayoA18 fatcat:4pq3lqrikbdonc6qe2kqgtvgxe

A Subword-Based Deep Learning Approach for Sentiment Analysis of Political Tweets

Marco Pota, Massimo Esposito, Marco A. Palomino, Giovanni L. Masala
2018 2018 32nd International Conference on Advanced Information Networking and Applications Workshops (WAINA)  
The successful use of online material in political campaigns over the past two decades has motivated the inclusion of social media platforms-such as Twitter-as an integral part of the political apparatus  ...  We are interested in learning how positive and negative opinions propagate through Twitter and how important events influence public opinion.  ...  Twitter Sentiment Analysis using a baseline method on the top and a CNN approach on the bottom We also used word clouds [20] to visualize the words included in the tweets that we collected and explain  ... 
doi:10.1109/waina.2018.00162 dblp:conf/aina/PotaEPM18 fatcat:kpc52mkuxnhrddcr2xp2lbr3le

How Polarized Have We Become? A Multimodal Classification of Trump Followers and Clinton Followers [chapter]

Yu Wang, Yang Feng, Zhe Hong, Ryan Berger, Jiebo Luo
2017 Lecture Notes in Computer Science  
As such, we treat polarization as a classification problem and study to what extent Trump followers and Clinton followers on Twitter can be distinguished, which in turn serves as a metric of polarization  ...  Inspired by this gaping polarization and the extensive utilization of Twitter during the 2016 presidential campaign, in this paper we take the first step in measuring polarization in social media and we  ...  Word embeddings map words into a higher dimensional vectors that can capture syntactic and semantic patterns and have been widely used in text classification tasks [27, 18] .  ... 
doi:10.1007/978-3-319-67217-5_27 fatcat:4pmab4fyyrbrxinqmj3d6y6pe4

When Politicians Talk About Politics: Identifying Political Tweets of Brazilian Congressmen [article]

Lucas S. Oliveira, Pedro O. S. Vaz de Melo, Marcelo S. Amaral, José Antônio. G. Pinho
2018 arXiv   pre-print
To evaluate our method, we used word clouds and a topic model to identify the main political and non-political latent topics in parliamentarian tweets.  ...  In midst of this crisis, Brazilian politicians use social media to communicate with the electorate in order to retain or to grow their political capital.  ...  Before running the classification methods, we execute a text embedding technique to transform every word in a numerical vector. We compare four text embedding techniques.  ... 
arXiv:1805.01589v1 fatcat:ghx5mhqmq5dlpjesyu7ouhewoq

Detection and Analysis of 2016 US Presidential Election Related Rumors on Twitter [article]

Zhiwei Jin, Juan Cao, Han Guo, Yongdong Zhang, Yu Wang, Jiebo Luo
2017 arXiv   pre-print
The 2016 U.S. presidential election has witnessed the major role of Twitter in the year's most important political event. Candidates used this social media platform extensively for online campaigns.  ...  The insights of this paper can help us understand the online rumor behaviors in American politics.  ...  "election" are the most mentioned words in the tweets.  ... 
arXiv:1701.06250v2 fatcat:mwxkvs26k5h2nh74xr27v4em3y

Biden vs Trump: Modelling US general elections using BERT language model

Rohitash Chandra, Ritij Saini
2021 IEEE Access  
In the case of the BERT model, we use inbuilt word embedding based on BERT-base uncased. D.  ...  These include 1.) pre-trained models such as embeddings from language models (ELMO) [66] that use complex characteristics such as syntax and semantics in word embedding and 2.) word embeddings such as  ... 
doi:10.1109/access.2021.3111035 fatcat:lgdckgzzrvghxnpug4megotkza

Automatic Detection and Categorization of Election-Related Tweets [article]

Prashanth Vijayaraghavan, Soroush Vosoughi, Deb Roy
2016 arXiv   pre-print
In this paper, we present and evaluate a technical framework, based on recent advances in deep neural networks, for identifying and analysing election-related conversation on Twitter on a continuous, longitudinal  ...  With the rise in popularity of public social media and micro-blogging services, most notably Twitter, the people have found a venue to hear and be heard by their peers without an intermediary.  ...  The model, though randomly initialized, will eventually learn a look-up matrix R |V |×d where |V | is the vocabulary size, which represents the word embedding for the words in the vocabulary.  ... 
arXiv:1605.05150v1 fatcat:2bg5pu5w4zcknj56b7jdun3flu

Embeddings-Based Clustering for Target Specific Stances: The Case of a Polarized Turkey [article]

Ammar Rashed, Mucahid Kutlu, Kareem Darwish, Tamer Elsayed, Cansın Bayrak
2022 arXiv   pre-print
users in an embedding space using Google's Convolutional Neural Network (CNN) based multilingual universal sentence encoder.  ...  During the election period, the Turkish people extensively shared their political opinions on Twitter.  ...  (Giatsoglou et al. 2017) trained a polarity classification model using word embeddings with a seed lexicon of polarity-labeled words.  ... 
arXiv:2005.09649v2 fatcat:udslijrkpvbfrfg7svjdb5jczy
« Previous Showing results 1 — 15 out of 4,952 results