Learning Word Vectors for Sentiment Analysis

By Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng, Christopher Potts. 2011

6,097 citations recorded by the source corpus.

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

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

In Representation & Self-Supervised Learning

Citations in the corpus

Adam: A Method for Stochastic Optimization (2014, methodology): “We examine the sparse feature problem using IMDB movie review dataset from (Maas et al., 2011).”
MaskGAN: Better Text Generation via Filling in the ______ (2018, methodology): “The IMDB dataset Maas et al. (2011) consists of 100,000 movie reviews taken from IMDB.”
Universal Language Model Fine-tuning for Text Classification (2018, methodology): “Sentiment Analysis For sentiment analysis, we evaluate our approach on the binary movie review IMDb dataset (Maas et al., 2011) and on the binary and five-class version of the Yelp review dataset compiled by Zhang et al.”
Learned in Translation: Contextualized Word Vectors (2017, methodology): “We train our model separately on two sentiment analysis datasets: the Stanford Sentiment Treebank (SST) [Socher et al., 2013] and the IMDb dataset [Maas et al., 2011].”
Semi-supervised Sequence Learning (2015, methodology): “In this ﬁrst set of experiments, we benchmark our methods on the IMDB movie sentiment dataset, proposed by Maas et al. [21].”
Distributed Representations of Sentences and Documents (2014, methodology): “Error rate BoW (bnc) (Maas et al., 2011) 12.20 % BoW (b ∆ t’c) (Maas et al., 2011) 11.77% LDA (Maas et al., 2011) 32.58% Full+BoW (Maas et al., 2011) 11.67% Full+Unlabeled+BoW (Maas et al., 2011) 11.11% WRRBM (Dahl et al., 2012) 12.58% WRRBM + BoW (bnc) (Dahl et al., 2012) 10.77% MNB-uni (Wang & Man”
Direct Preference Optimization: Your Language Model is Secretly a Reward Model (2023, background): “In controlled sentiment generation , x is a preﬁx of a movie review the IMDb dataset [22], and the policy must generate y with positive sentiment.”
StereoSet: Measuring stereotypical bias in pretrained language models (2020, methodology): “In order to evaluate sentiment, we ﬁne-tune BERT (Devlin et al., 2019) on movie reviews (Maas et al., 2011)”
Pretrained Transformers Improve Out-of-Distribution Robustness (2020, methodology): “For STS-B, ReCoRD, and SST-2/IMDb, there is a noticeable drop in accuracy when testing on OOD examples.”
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter (2019, methodology): “Downstream tasks We further study the performances of DistilBERT on several downstream tasks under efﬁcient inference constraints: a classiﬁcation task (IMDb sentiment classiﬁcation - Maas et al. [2011]) and a question answering task (SQuAD v1.”
Unsupervised Data Augmentation for Consistency Training (2019, methodology): “For language, we rely on six text classification benchmark datasets, including IMDb, Yelp-2, Yelp-5, Amazon-2 and Amazon5 sentiment classification and DBPedia topic classification (Maas et al., 2011; Zhang et al., 2015).”
Efficient Estimation of Word Representations in Vector Space (2013, methodology): “r 50% increase in Spearman’s rank correlation over the previous best result [31]. The neural network based word vectors were previously applied to many other NLP tasks, for example sentiment analysis [12] and paraphrase detection [28]. It can be expected that these applications can beneﬁt from the m”
Fine-tuned Language Models for Text Classification (2018, methodology): “Sentiment Analysis For sentiment analysis, we evaluate our approach on the binary movie review IMDb dataset (Maas et al., 2011) and on the binary Yelp review dataset compiled by Zhang et al. (2015).”
Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function (2019, methodology): “ACL-IMDB (Maas et al. 2011) and Elec (JZ15a) datasets are widely used for binary sentiment classiﬁcation of movie reviews and Amazon product reviews respectively while AG-News , DBpedia (Zhang, Zhao, and LeCun 2015), and RCV1 (Lewis et al. 2004) are for topic classiﬁcation of news articles,…”
Adversarial Training Methods for Semi-Supervised Text Classification (2016, background): “Figure 2 shows the learning curves on the IMDB test set with the baseline method (only embedding dropout and pretraining 6)) and (c) virtual adversarial loss (deﬁned in Eq.”
Finetuned Language Models Are Zero-Shot Learners (2021, neutral): “IMDB (Maas et al., 2011) 2.”
Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus (2021, neutral): “1290 dataset (Maas et al., 2011) and the CNN/DailyMail summarization dataset (Hermann et al.”