Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions
Explore this paper's citation graph
Summary
A novel machine learning framework based on recursive autoencoders for sentence-level prediction of sentiment label distributions that outperform other state-of-the-art approaches on commonly used datasets, without using any pre-defined sentiment lexica or polarity shifting rules.
- Type
- article
- Published
- 2011-07-27
- Cited by
- 1,360
- References
- 41
- OpenAlex
- https://openalex.org/W71795751
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:3116311
Keywords
Computer science, Sentiment analysis, Artificial intelligence, Sentence, Multinomial distribution
References
- Coupling Niche Browsers and Affect Analysis for an Opinion Mining Application
- Crystal: Analyzing Predictive Opinions on the Web
- Multiple Aspect Ranking Using the Good Grief Algorithm
- Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews
- Parsing Natural Scenes and Natural Language with Recursive Neural Networks
- On the negativity of negation
- A holistic lexicon-based approach to opinion mining
- Recursive Distributed Representations
- Learning to Shift the Polarity of Words for Sentiment Classification
- Annotating Expressions of Opinions and Emotions in Language
- Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis
- Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying the Polarity of Opinion Sentences
- The general inquirer: A computer approach to content analysis.
- Distributed representations, simple recurrent networks, and grammatical structure
- The viability of web-derived polarity lexicons
- A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts
- Mining the peanut gallery: opinion extraction and semantic classification of product reviews
- A unified architecture for natural language processing: deep neural networks with multitask learning
- Linear recursive distributed representations
- Dependency Tree-based Sentiment Classification using CRFs with Hidden Variables
Cited by
- Semantics, Modelling, and the Problem of Representation of Meaning - a Brief Survey of Recent Literature
- Semi-supervised extractive speech summarization via co-training algorithm
- Fast dropout training
- A Comparison of Vector-based Representations for Semantic Composition
- Transition-based Dependency Parsing Using Recursive Neural Networks
- Predicting Linguistic Structure with Incomplete and Cross-Lingual Supervision
- Rule-based Emotion Detection on Social Media: Putting Tweets on Plutchik's Wheel
- Modeling Techniques in Predictive Analytics: Business Problems and Solutions with R
- A LOCATION-AWARE SOCIAL MEDIA MONITORING SYSTEM
- Joint Author Sentiment Topic Model
- Author-Specific Sentiment Aggregation for Polarity Prediction of Reviews
- Vector Space Semantic Parsing: A Framework for Compositional Vector Space Models
- Modelling input texts: from Tree Kernels to Deep Learning
- Effectively classifying short texts by structured sparse representation with dictionary filtering
- Mining Supportive and Unsupportive Evidence from Facebook Using Anti-Reconstruction of the Nuclear Power Plant as an Example
- Learning Task-specific Bilexical Embeddings
- Answer Extraction by Recursive Parse Tree Descent
- Adapted competitive learning on continuous semantic space for word sense induction
- Effective deep learning-based multi-modal retrieval
- Hyperspectral classification via deep networks and superpixel segmentation
Related papers
- Efficient Estimation of Word Representations in Vector Space
- Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
- GloVe: Global Vectors for Word Representation
- Thumbs up? Sentiment Classification using Machine Learning Techniques
- Seeing Stars: Exploiting Class Relationships for Sentiment Categorization with Respect to Rating Scales
- Mining and summarizing customer reviews
- Natural Language Processing (Almost) from Scratch
- Word Representations: A Simple and General Method for Semi-Supervised Learning
- Distributed Representations of Words and Phrases and their Compositionality