Twitter Sentiment Classiﬁcation using Distant Supervision

By Alec Go. 2009

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

A Convolutional Neural Network for Modelling Sentences (2014, methodology): “Section 4 treats of the induced feature graph and other properties of the network.”
Finetuned Language Models Are Zero-Shot Learners (2021, neutral): “Sentiment140 (Go et al., 2009) 3.”
Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models (2021, background): “, 2011)), improving it on Twitter data (Senti140 and SemEval 2017 (Go et al., 2009; Nakov et al., 2013)) and contrast sets (Gardner et al.”
Concrete Problems in AI Safety (2016, background): “…approaches in the presence of model mis-speciﬁcation — for instance, there is a large empirical literature showing that generative approaches to semi-supervised learning based on maximizing marginal likelihood can perform very poorly when the model is mis-speciﬁed [96, 108, 34, 88, 86].”
Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm (2017, methodology): “Instead we pretrain a model with the hyperparameters of the largest model in their ensemble on the positive/negative emoticon dataset from Go et al. (2009).”
Federated Optimization in Heterogeneous Networks (2018, methodology): “• Sent140: In non-convex settings, we consider a text sentiment analysis task on tweets from Sentiment140 (Go et al., 2009) (Sent140) with a two layer LSTM binary classifier containing 256 hidden units with pretrained 300D GloVe embedding (Pennington et al., 2014).”
Robust Aggregation for Federated Learning (2019, methodology): “(c) Sentiment Analysis: We use the Sent140 dataset [36] where the input x is a tweet and the output y = ±1 is its sentiment.”
Fair Resource Allocation in Federated Learning (2019, background): “• Sent140: This dataset is a collection of tweets from Sentiment140 [15] (Sent140).”
Semi-Cyclic Stochastic Gradient Descent (2019, methodology): “To illustrate the challenges of optimizing on block-cyclic data, we train and evaluate a small logistic regression model on the Sentiment140 Twitter dataset (Go et al., 2009), a binary classification task over 1.”
Federated Heavy Hitters Discovery with Differential Privacy (2019, methodology): “We use the Sentiment140 dataset, a Twitter dataset with 1.6M tweets and over 650k users Go et al. (2009).”
LEAF: A Benchmark for Federated Settings (2018, background): “• Sentiment140 [9], an automatically generated sentiment analysis dataset that annotates tweets based on the emoticons present in them.”
Distilled One-Shot Federated Learning (2020, methodology): “To show that DOSFL is not limited to image-based tasks, we test DOSFL on federated IMDB (sentiment analysis) [21], federated TREC-6 (question classiﬁcation) [35], and federated Sent140 (sentiment analysis) [8].”
Federated Meta-Learning with Fast Convergence and Efficient Communication (2018, background): “(3) Sentiment140 [6] for 2-class sentiment classiﬁcation, which is automatically generated by annotating tweets based on the emoticons presented in them.”
SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer (2021, positive): “• Sentiment analysis, including CR (Hu and Liu, 2004), GOEMOTIONS (Demszky et al., 2020), SENTIMENT140 (Go et al., 2009), SST-2, and YELP-2 (Zhang et al., 2015).”
CARER: Contextualized Affect Representations for Emotion Recognition (2018, methodology): “We bootstrap a set of noisy labels to obtain large-scale emotion tweets, and then perform annotation via distant supervision as in (Go et al., 2009; González-Ibánez et al., 2011; Wang et al., 2012; Mohammad and Kiritchenko, 2015; Abdul-Mageed and Ungar, 2017).”
Language Models are General-Purpose Interfaces (2022, background): “• Sentiment Classiﬁcation is to determine the emotional tone of a piece of text, whether it is positive or negative: IMDB (Maas et al., 2011), SST-2 (Socher et al., 2013), Sentiment140 (Go et al., 2009), Yelp (Zhang et al., 2015).”
Representation Stability as a Regularizer for Improved Text Analytics Transfer Learning (2017, positive): “…to be the binary ( Emoticon Heuristic: Finally, we consider a semi-supervised task based on emoticon prediction motivated by the successful work in (Go et al., 2009), leveraging it in the twitter sentiment domain and its use as a vital component of the SemEval competition winning system (Bethard…”
Addressing Age-Related Bias in Sentiment Analysis (2018, methodology): “Some feature automatic tweet annotation based on the inclusion of specific emoticons [28], while others employ trained annotators using criteria for removing inconsistent or inaccurate annotations [35].”