Predicting Polarities of Tweets by Composing Word Embeddings with Long Short-Term Memory

Wang, Xin; Liu, Yuanchao; Sun, Chengjie; Wang, Baoxun; Wang, Xiaolong

doi:10.3115/v1/p15-1130

Cited by 255 publications

(105 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) RNN for sentence-level classification: Wang et al [25] proposed encoding entire tweets with LSTM, whose hidden state is used for predicting sentiment polarity. This simple strategy proved competitive to the more complex DCNN structure by Kalchbrenner et al [49] designed to endow CNN models with ability to capture long-term dependencies.…”

Section: B Rnn Modelsmentioning

confidence: 99%

Recent Trends in Deep Learning Based Natural Language Processing [Review Article]

Young

Hazarika

Poria

et al. 2018

IEEE Comput. Intell. Mag.

2,730

1,307

View full text Add to dashboard Cite

Deep learning methods employ multiple processing layers to learn hierarchical representations of data, and have produced state-of-the-art results in many domains. Recently, a variety of model designs and methods have blossomed in the context of natural language processing (NLP). In this paper, we review significant deep learning related models and methods that have been employed for numerous NLP tasks and provide a walk-through of their evolution. We also summarize, compare and contrast the various models and put forward a detailed understanding of the past, present and future of deep learning in NLP.

show abstract

Section: B Rnn Modelsmentioning

confidence: 99%

Recent Trends in Deep Learning Based Natural Language Processing [Review Article]

Young

Hazarika

Poria

et al. 2018

IEEE Comput. Intell. Mag.

2,730

1,307

View full text Add to dashboard Cite

show abstract

“…Deep learning has emerged as a powerful machine learning technique and is also popularly used in sentiment analysis in recent years [14], [15]. Wang et al proposed a CNN-RNN architecture [16] to analyze the sentiment of short text while some other studies tried apply methods based on CNN [17] and RNN [18]. Their experimental results shown that the proposed method outperforms lexicon-based, regression-based, and obtained an obvious improvement upon the state-of-the-art.…”

Section: Literature Surveymentioning

confidence: 99%

Uncovering Flaming Events on News Media in Social Media

Rajapaksha¹,

Farahbakhsh²,

Crespi³

et al. 2019

2019 IEEE 38th International Performance Computing and Communications Conference (IPCCC)

View full text Add to dashboard Cite

Social networking sites (SNSs) facilitate the sharing of ideas and information through different types of feedback including publishing posts, leaving comments and other type of reactions. However, some comments or feedback on SNSs are inconsiderate and offensive, and sometimes this type of feedback has a very negative effect on a target user. The phenomenon known as flaming goes hand-in-hand with this type of posting that can trigger almost instantly on SNSs. Most popular users such as celebrities, politicians and news media are the major victims of the flaming behaviors and so detecting these types of events will be useful and appreciated. Flaming event can be monitored and identified by analyzing negative comments received on a post. Thus, our main objective of this study is to identify a way to detect flaming events in SNS using a sentiment prediction method. We use a deep Neural Network (NN) model that can identity sentiments of variable length sentences and classifies the sentiment of SNSs content (both comments and posts) to discover flaming events. Our deep NN model uses Word2Vec and FastText word embedding methods as its training to explore which method is the most appropriate. The labeled dataset for training the deep NN is generated using an enhanced lexicon based approach. Our deep NN model classifies the sentiment of a sentence into five classes: Very Positive, Positive, Neutral, Negative and Very Negative. To detect flaming incidents, we focus only on the comments classified into the Negative and Very Negative classes. As a use-case, we try to explore the flaming phenomena in the news media domain and therefore we focused on news items posted by three popular news media on Facebook (BBCNews, CNN and FoxNews) to train and test the model. The experimental results show that flaming events can be detected with our proposed approach, and we explored main characteristics that trigger a flaming event and topics discussed in the flaming posts.

show abstract

“…In terms of methods, we believe that deep learning [58,61,72], together with semi-supervised and distantly-supervised methods [10,67], will be the main focus of future research. We also expect more attention to be paid to linguistic structure and sentiment compositionality [62,63].…”

Section: Future Directionsmentioning

confidence: 99%

“…A popular way to solve this latter problem is to use self training, a form of semi-supervised learning, where first a system is trained on the available training data only, then this system is applied to make predictions on a large unannotated set of tweets, and finally it is trained for a few more iterations on its own predictions. This works because parts of the network, e.g., with convolution or with LSTMs [58,61,72], need to learn something like a language model, i.e., which word is likely to follow which one. Training these parts needs no labels.…”

Section: Features and Learningmentioning

confidence: 99%

Semantic Sentiment Analysis of Twitter Data

Nakov¹

2017

Encyclopedia of Social Network Analysis and Mining

View full text Add to dashboard Cite

Microblog sentiment analysis; Twitter opinion mining 2 GlossarySentiment Analysis: This is text analysis aiming to determine the attitude of a speaker or a writer with respect to some topic or the overall contextual polarity of a piece of text. DefinitionSentiment analysis on Twitter is the use of natural language processing techniques to identify and categorize opinions expressed in a tweet, in order to determine the author's attitude toward a particular topic or in general. Typically, discrete labels such as positive, negative, neutral, and objective are used for this purpose, but it is also possible to use labels on an ordinal scale, or even continuous numerical values.

show abstract

Predicting Polarities of Tweets by Composing Word Embeddings with Long Short-Term Memory

Cited by 255 publications

References 24 publications

Recent Trends in Deep Learning Based Natural Language Processing [Review Article]

Recent Trends in Deep Learning Based Natural Language Processing [Review Article]

Uncovering Flaming Events on News Media in Social Media

Semantic Sentiment Analysis of Twitter Data

Contact Info

Product

Resources

About