Twitter Sentiment Analysis with Deep Convolutional Neural Networks

By Aliaksei Severyn, Alessandro Moschitti. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2015

653 citations recorded by the source corpus.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/bffcc7a78114915d8844cb80adefa56c650e213e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

AI Benchmark: Running Deep Neural Networks on Android Smartphones (2018, background): “Another group of tasks encompasses various natural language processing problems such as natural language translation [18, 19], sentence completion [20, 21], sentence sentiment analysis [22, 23] or interactive chatbots [24].”
Encoding Syntactic Knowledge in Neural Networks for Sentiment Classification (2017, background): “There are a few works on automatic construction of such lexicons [Severyn and Moschitti 2015a; Chen and Skiena 2014; Vo and Zhang 2016], however, to the best of our knowledge, there is still not much work reported on how such lexicon resources can be seamlessly integrated with neural networks.”
FinBERT: Financial Sentiment Analysis with Pre-trained Language Models (2019, methodology): “We can divide the recent efforts into two groups: 1) Machine learning methods with features extracted from text with "word counting" [1, 19, 28, 30], 2) Deep learning methods, where text is represented by a sequence of embeddings [2, 25, 32].”
Sentiment Embeddings with Applications to Sentiment Analysis (2016, background): “Sentence level sentiment classiﬁcation on tweets [21], [22] and reviews [23] help us understand whether sentiment embeddings are helpful in capturing discriminative features for predict the sentiment of text.”
Interpretable Convolutional Neural Networks with Dual Local and Global Attention for Review Rating Prediction (2017, methodology): “Most networks use word embeddings [12, 22, 24, 25, 28] as the input layer, while [5, 7, 29] used character embeddings, especially [5] uses very deep (29 layers) CNNs on character embeddings and shows impressive results on text classi cation, including the Amazon reviews.”
A clinical text classification paradigm using weak supervision and deep representation (2019, background): “Furthermore, weak supervision has been widely applied in other common NLP tasks including knowledge-base completion [28], sentiment analysis [29], and information retrieval [30].”
Sentiment Analysis Using Deep Learning Techniques: A Review (2017, background): “The authors [26] have proposed the system of deep learning for sentiment analysis of twitter.”
Data Boost: Text Data Augmentation through Reinforcement Learning Guided Conditional Generation (2020, background): “, 2017; Cliche, 2017), is reported to have severe overfitting problems when given extremely limited training data (Elming et al., 2014; Severyn and Moschitti, 2015).”
Text feature extraction based on deep learning: a review (2017, background): “…language processing) tasks, such as semantic parsing [43], information retrieval [44, 45], semantic role labeling [46, 47], sentimental analysis [48], question answering [49 – 52], machine translation [53 – 56], text classification [57], summarization [58, 59], and text generation [60], as well…”
Improving Hate Speech Detection with Deep Learning Ensembles (2018, methodology): “…is worth exploration by NLP and text mining researchers, as the work of (Badjatiya et al., 2017; Gamb¨ack and Sikdar, 2017; Park and Fung, 2017; Severyn and Moschitti, 2015; Stojanovski et al., 2015; Vosoughi et al., 2016; Yang and Eisenstein, 2017) are just some examples demonstrating strong…”
Context Mover's Distance & Barycenters: Optimal transport of contexts for building representations (2018, methodology): “Pre-trained unsupervised representations in particular have been immensely useful as general purpose features for model initialization (Kim, 2014), downstream tasks, (Severyn & Moschitti, 2015; Deriu et al., 2017) and in domains with limited supervised information (Qi et al., 2018).”
Semantic Text Matching for Long-Form Documents (2019, background): “For instance, some studies [2, 27, 32, 33, 45, 46] exploit RNNs to model the sequential information of documents while other work [19, 38, 46, 54] applies CNNs to capture the important local messages in documents for semantic text matching.”
Do Convolutional Networks need to be Deep for Text Classification ? (2017, background): “Other works (Severyn and Moschitti 2015) further noted that word-based input representations may not be very well adapted to social media inputs like Twitter, where tokens usage may be extremely creative: slang, elongated words, contiguous sequences of exclamation marks, abbreviations, hashtags,.”
Arming the public with artificial intelligence to counter social bots (2019, background): “Deep-learning approaches can also be used to detect sentiment online (Socher et al., 2013; Tang et al., 2014; Severyn and Moschitti, 2015), allowing the next generation of social bots to be more perceptive about human emotions.”
Bi-LSTM Model to Increase Accuracy in Text Classification: Combining Word2vec CNN and Attention Mechanism (2020, methodology): “Early 2D CNNs have been widely used in image processing, but they have only recently been used in text classification tasks and have outperformed sequence-based approaches [12].”
Learning From Noisy Labels With Deep Neural Networks: A Survey (2020, background): “W ITH the recent emergence of large-scale datasets, deep neural networks (DNNs) have exhibited impressive performance in numerous machine learning tasks, such as computer vision [1], [2], information retrieval [3]–[5], and language processing [6]–[8].”
Harnessing Multi-Source Data about Public Sentiments and Activities for Informed Design (2019, background): “(Convolutional Neural Network) [16] and FastText [25].”