A Dynamic Conditional Random Field Based Framework for Sentence-Level Sentiment Analysis of Chinese Microblog
Published 1 July 2017
Zhifeng Hao, Ruichu Cai, Yiyang Yang, Wen Wen, Lixin Liang
Citations11
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
WDCRF: a Word2vec and Dynamic Conditional Random Field (DCRF) based framework for Sentiment Analysis of Chinese Microblog achieves much better than the state-of-the-art.
Abstract
With the increasing popularity of social media, the Sentiment Analysis (SA) of the Microblog has raised as a new research topic. In this paper, we present WDCRF: a Word2vec and Dynamic Conditional Random Field (DCRF) based framework for Sentiment Analysis of Chinese Microblog. Our contributions include: firstly, to address drawbacks of Microblog message such as the length and Lexicon limitations, Word2vec technology is leveraged to enrich Microblog message so that each word individual is extended by its Top-k similar words. Secondly, DCRF model is utilized to combine and conduct the Subjectivity Classification and Polarity Classification simultaneously, while in existing works they are designed as independent and the relationship between two types of classifications is ignored. Moreover, the DCRF model considers not only the classification-level relationship but also the relationship between neighboring sentences. Finally, the experiments on real dataset collected from Sina and Tencent Weibo demonstrate that our WDCRF (Word2vec + DCRF) achieves much better than the state-of-the-art.
Keywords
Computer Science
ScienceReducing the Dimensionality of Data with Neural Networks
20,953 Citations2006Geoffrey E. Hinton, Ruslan Salakhutdinov
arXiv (Cornell University)Distributed Representations of Words and Phrases and their Compositionality
18,086 Citations2013Tomáš Mikolov, Ilya Sutskever +3 more
This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.
arXiv (Cornell University)Efficient Estimation of Word Representations in Vector Space
18,050 Citations2013Tomáš Mikolov, Kai Chen +2 more
Two novel model architectures for computing continuous vector representations of words from very large data sets are proposed and it is shown that these vectors provide state-of-the-art performance on the authors' test set for measuring syntactic and semantic word similarities.
ScholarlyCommons (University of Pennsylvania)Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
12,978 Citations2001John Lafferty, Andrew McCallum +1 more
This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.
arXiv (Cornell University)Efficient Estimation of Word Representations in Vector Space
11,710 Citations2013Tomáš Mikolov, Kai Chen +2 more
Thumbs up?
6,987 Citations2002Bo Pang, Lillian Lee +1 more
This work considers the problem of classifying documents not by topic, but by overall sentiment, e.g., determining whether a review is positive or negative, and concludes by examining factors that make the sentiment classification problem more challenging.
Proceedings of the International AAAI Conference on Web and Social MediaVADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text
5,749 Citations2014Cecelia Hutto, Éric Gilbert
Interestingly, using the authors' parsimonious rule-based model to assess the sentiment of tweets, it is found that VADER outperforms individual human raters, and generalizes more favorably across contexts than any of their benchmarks.
Meeting of the Association for Computational LinguisticsThumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews
3,654 Citations2002Peter Peter, Turney
Linguistic Regularities in Continuous Space Word Representations
2,882 Citations2013Tomáš Mikolov, Wen-tau Yih +1 more
The vector-space word representations that are implicitly learned by the input-layer weights are found to be surprisingly good at capturing syntactic and semantic regularities in language, and that each relationship is characterized by a relation-specific vector offset.
arXiv (Cornell University)Thumbs up? Sentiment Classification using Machine Learning Techniques
2,208 Citations2002Bo Pang, Lillian Lee +1 more
ArXiv.orgThumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews
1,585 Citations2002Peter D. Turney
Shallow parsing with conditional random fields
1,251 Citations2003Fei Sha, Fernando Pereira
This work shows how to train a conditional random field to achieve performance as good as any reported base noun-phrase chunking method on the CoNLL task, and better than any reported single model.
Robust Sentiment Detection on Twitter from Biased and Noisy Data
875 Citations2010Luciano Barbosa, Junlan Feng
This paper proposes an approach to automatically detect sentiments on Twitter messages (tweets) that explores some characteristics of how tweets are written and meta-information of the words that compose these messages and leverages sources of noisy labels as training data.
Target-dependent Twitter Sentiment Classification
846 Citations2011Long Jiang, Mo Yu +3 more
This paper proposes to improve target-dependent Twitter sentiment classification by incorporating target- dependent features; and taking related tweets into consideration; and according to the experimental results, this approach greatly improves the performance of target- dependence sentiment classification.
International Conference on Artificial Intelligence and StatisticsHierarchical Probabilistic Neural Network Language Model.
840 Citations2005Fréderic Morin, Yoshua Bengio
A point-of-care POC analyzer that can rapidly measure both medications used for treatment and illicit drugs in patient saliva and shows evidence of accuracy in measuring treatment medications and relapse to drug use is shown.
Discriminative probabilistic models for relational data
637 Citations2002Ben Taskar, Pieter Abbeel +1 more
Dimensional Sentiment Analysis Using a Regional CNN-LSTM Model
587 Citations2016Jin Wang, Liang Yu +2 more
A regional CNN-LSTM model consisting of two parts: regional CNN and LSTM to predict the VA ratings of texts is proposed, showing that the proposed method outperforms lexicon-based, regression- based, and NN-based methods proposed in previous studies.
Scalable training of<i>L</i><sup>1</sup>-regularized log-linear models
541 Citations2007Galen Andrew, Jianfeng Gao
This work presents an algorithm Orthant-Wise Limited-memory Quasi-Newton (OWL-QN), based on L-BFGS, that can efficiently optimize the L1-regularized log-likelihood of log-linear models with millions of parameters.
Edinburgh Research Explorer (University of Edinburgh)Dynamic Conditional Random Fields: Factorized Probabilistic Models for Labeling and Segmenting Sequence Data
292 Citations2007Charles Sutton, Andrew McCallum +1 more
On a natural-language chunking task, it is shown that a DCRF performs better than a series of linear-chain CRFs, achieving comparable performance using only half the training data.
Topic Modeling based Sentiment Analysis on Social Media for Stock Market Prediction
250 Citations2015Thien Hai Nguyen, Kiyoaki Shirai
The results show that incorporation of the sentiment information from social media can help to improve the stock prediction.
IEEE Transactions on Information TheorySufficient Conditions for Convergence of the Sum–Product Algorithm
223 Citations2007Joris M. Mooij, Hilbert J. Kappen
Novel conditions are derived that guarantee convergence of the Sum-Product algorithm to a unique point, irrespective of the initial messages, and are shown to be valid also in the case of factors containing zeros, under some additional conditions.
International Conference on Computational LinguisticsBuilding Large-Scale Twitter-Specific Sentiment Lexicon : A Representation Learning Approach
158 Citations2014Duyu Tang, Furu Wei +3 more
The sentiment lexicon (TS-Lex) is built with a dedicated neural architecture and integrates the sentiment information of text into its hybrid loss function for learning sentiment-specific phrase embedding (SSPE).
NeurocomputingActive deep learning method for semi-supervised sentiment classification
149 Citations2013Shusen Zhou, Qingcai Chen +1 more
Experiments on five sentiment classification datasets show that ADN and IADN outperform classical semi-supervised learning algorithms, and deep learning techniques applied for sentiment classification.
Cognitive ComputationTwitter Sentiment Analysis for Large-Scale Data: An Unsupervised Approach
144 Citations2014Rafeeque Pandarachalil, S. Sendhilkumar +1 more
An unsupervised method for analysing tweet sentiments that is implemented and tested in parallel python framework and shown to scale well with large volume of data on multiple cores.
IEEE Transactions on Knowledge and Data EngineeringLearning distributed representations of concepts using linear relational embedding
130 Citations2001Alberto Paccanaro, Geoffrey E. Hinton
Context-aware Learning for Sentence-level Sentiment Analysis with Posterior Regularization
126 Citations2014Bishan Yang, Claire Cardie
A novel context-aware method for analyzing sentiment at the level of individual sentences that encoding intuitive lexical and discourse knowledge as expressive constraints and integrating them into the learning of conditional random field models via posterior regularization is proposed.
Improving Twitter Sentiment Analysis with Topic-Based Mixture Modeling and Semi-Supervised Training
92 Citations2014Bing Xiang, Liang Zhou
The proposed sentiment model outperforms the top system in the task of Sentiment Analysis in Twitter in SemEval-2013 in terms of averaged F scores.
A context-based model for Sentiment Analysis in Twitter
87 Citations2014Andrea Vanzo, Danilo Croce +1 more
A Markovian formulation of the Support Vector Machine discriminative model as embodied by the SVM hmm algorithm has been here employed to assign the sentiment polarity to entire sequences and proves that sequential tagging effectively embodies evidence about the contexts.
Zhongwen xinxi xuebaoHierarchical Structure Based Hybrid Approach to Sentiment Analysis of Chinese Micro Blog and Its Feature Extraction
48 Citations2012Zhou Ming
This paper utilizes micro blog API from Sina and carries out sentiment analysis on Chinese micro blog to compare performances of three method, based on the emoticon, the sentiment lexicon and the hybrid approach over hierarchical structure using SVM, respectfully.
ReNew: A Semi-Supervised Framework for Generating Domain-Specific Lexicons and Sentiment Analysis
30 Citations2014Zhe Zhang, Munindar P. Singh
This work proposes a semi-supervised framework for generating a domain-specific sentiment lexicon and inferring sentiments at the segment level and achieves approximately 1% greater accuracy than a state-of-the-art approach based on elementary discourse units.
Learning to Adapt Credible Knowledge in Cross-lingual Sentiment Analysis
29 Citations2015Qiang Chen, Wenjie Li +3 more
This paper proposes to integrate into knowledge transfer a knowledge validation model, which aims to prevent the negative influence from the wrong knowledge by distinguishing highly credible knowledge in cross-lingual sentiment analysis.
A system for fine-grained aspect-based sentiment analysis of Chinese
22 Citations2015Janna Lipenkova
A pipeline for aspectbased sentiment analysis of Chinese texts in the automotive domain is presented to demonstrate how knowledge about sentence structure can increase the precision, insight value and granularity of the output.
Construction of an Evaluation Corpus for Opinion Extraction
17 Citations2005Lun‐Wei Ku, Tung-Ho Wu +2 more
This paper defines the annotation of opinionated material and develops an opinion extraction system that employs opinion holders, a topic’s conceptual words, sentiment words, opinion operators, and negation operators to recognize opinions.