Unsupervised sentiment analysis with emotional signals

@article{Hu2013UnsupervisedSA,
  title={Unsupervised sentiment analysis with emotional signals},
  author={Xia Hu and Jiliang Tang and Huiji Gao and Huan Liu},
  journal={Proceedings of the 22nd international conference on World Wide Web},
  year={2013}
}
  • Xia Hu, Jiliang Tang, Huan Liu
  • Published 13 May 2013
  • Computer Science
  • Proceedings of the 22nd international conference on World Wide Web
The explosion of social media services presents a great opportunity to understand the sentiment of the public via analyzing its large-scale and opinion-rich data. [] Key Result In the experiment, we compare the proposed framework with the state-of-the-art methods on two Twitter datasets and empirically evaluate our proposed framework to gain a deep understanding of the effects of emotional signals.

Figures and Tables from this paper

Unsupervised Sentiment Analysis with Signed Social Networks
TLDR
This paper incorporates explicit sentiment signals in textual terms and implicit sentiment signals from signed social networks into a coherent model SignedSenti for unsupervised sentiment analysis, and empirical experiments corroborate its effectiveness.
Sentiment and Emotion Analysis for Social Multimedia: Methodologies and Applications
TLDR
This research attempts to analyze the online sentiment changes of social media users using both the textual and visual content and focuses on sentiment analysis based on visual and multimedia information analysis.
emoji training heuristic for multi-class sentiment analysis on Twitter with a Multinomial Naive Bayes Classifier
TLDR
A new framework ESD is proposed, which simultaneously captures various signals from text and emojis for sarcasm detection, and experimental results on real-world datasets demonstrate the effectiveness of the proposed framework.
Comparing and combining sentiment analysis methods
TLDR
A new method that combines existing approaches, providing the best coverage results and competitive agreement is developed and a free Web service called iFeel is presented, which provides an open API for accessing and comparing results across different sentiment methods for a given text.
Sentiment Analysis in Social Media Platforms: The Contribution of Social Relationships
TLDR
A sentiment analysis framework that considers the social relationships among users and contents is proposed and results indicate that it can more accurately classify sentiment of sentences by utilizing social relationships.
Unsupervised Sentiment Analysis for Social Media Images
TLDR
This paper proposes a novel Unsupervised SEntiment Analysis (USEA) framework for social media images that exploits relations among visual content and relevant contextual information to bridge the "semantic gap" in prediction of image sentiments.
An Overview of Sentiment Analysis in Social Media and Its Applications in Disaster Relief
TLDR
This chapter explores applications of sentiment analysis and demonstrates how sentiment mining in social media can be exploited to determine how local crowds react during a disaster, and how such information can be used to improve disaster management.
Propagation-based Sentiment Analysis for Microblogging Data
TLDR
This paper provides a propagating process to incorporate various types of emotional signals in microblogging data into a coherent model, and proposes a novel sentiment analysis framework PSA which learns from both labeled and unlabeled data by iteratively alternating a propagates process and a fitting process.
...
...

References

SHOWING 1-10 OF 46 REFERENCES
Exploiting social relations for sentiment analysis in microblogging
TLDR
This work proposes a Sociological Approach to handling Noisy and short Texts (SANT) for sentiment classification and presents a mathematical optimization formulation that incorporates the sentiment consistency and emotional contagion theories into the supervised learning process.
Generate Adjective Sentiment Dictionary for Social Media Sentiment Analysis Using Constrained Nonnegative Matrix Factorization
TLDR
An automatic sentiment dictionary generation method, called Constrained Symmetric Nonnegative Matrix Factorization (CSNMF) algorithm, to assign polarity scores to each word in the dictionary, on a large social media corpus - digg.com.
MoodLens: an emoticon-based sentiment analysis system for chinese tweets
TLDR
MoodLens is the first system for sentiment analysis of Chinese tweets in Weibo, and by using the highly efficient Naive Bayes classifier, MoodLens is capable of online real-time sentiment monitoring.
Emoticon Smoothed Language Models for Twitter Sentiment Analysis
TLDR
A novel model, called emoticon smoothed language model (ESLAM), is presented, which is to train a language model based on the manually labeled data, and then use the noisy emoticon data for smoothing.
A Survey of Opinion Mining and Sentiment Analysis
TLDR
A survey is presented which covers the problem of sentiment analysis, techniques and methods used for the same and the major challenge lies in analyzing the sentiments and identifying emotions expressed in texts.
Automatic construction of a context-aware sentiment lexicon: an optimization approach
TLDR
This paper proposes a novel optimization framework that provides a unified and principled way to combine different sources of information for learning a context-dependent sentiment lexicon that is not only domain specific but also dependent on the aspect in context given an unlabeled opinionated text collection.
Twitter mood predicts the stock market
Bridging Domains with Words: Opinion Analysis with Matrix Tri-factorizations
TLDR
This paper outlines a novel sentiment transfer mechanism based on constrained non-negative matrix tri-factorizations of termdocument matrices in the source and target domains and obtains promising empirical results with this approach.
A Survey of Opinion Mining and Sentiment Analysis
Sentiment analysis or opinion mining is the computational study of people’s opinions, appraisals, attitudes, and emotions toward entities, individuals, issues, events, topics and their attributes.
What Were the Tweets About? Topical Associations between Public Events and Twitter Feeds
TLDR
An analytical method based on joint statistical modeling of topical influences from the events and associated Twitter feeds enables the auto-segmentation of the Events and the characterization of tweets into two categories: episodic tweets that respond specifically to the content in the segmentsof the events, and steady tweets that responded generally about the events.
...
...