AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
We extract sentiment relations between tweets based on social theories, and model the relations using graph Laplacian, which is employed as a regularization to a sparse formulation

Exploiting social relations for sentiment analysis in microblogging

WSDM, pp.537-546, (2013)

Cited by: 407|Views193
EI

Abstract

Microblogging, like Twitter and Sina Weibo, has become a popular platform of human expressions, through which users can easily produce content on breaking news, public events, or products. The massive amount of microblogging data is a useful and timely source that carries mass sentiment and opinions on various topics. Existing sentiment a...More

Code:

Data:

0
Introduction
  • Microblogging services are extensively used to share information or opinions in various domains.
  • The sheer volumes of microblogging data present opportunities and challenges for sentiment analysis of these noisy and short texts.
  • Sentiment analysis has been extensively studied for product and movie reviews [32], which differ substantially from microblogging data.
  • When composing a microblogging message, users may use or coin new abbreviations or acronyms that seldom appear in conventional text documents.
  • Messages like “It is coooooool”, “OMG :-(”, are intuitive and popular in microblogging, but some are not formal words.
  • Existing methods [2, 8] rely on pre-defined sentiment vocabularies [39], which are highly domain-specific
Highlights
  • Microblogging services are extensively used to share information or opinions in various domains
  • We introduce our formulation to utilize social relations for sentiment analysis, and answer the question: “How can social relations be explicitly integrated into the sentiment classification framework?”
  • We propose a novel sociological approach (SANT ) to handle networked texts in microblogging
  • We extract sentiment relations between tweets based on social theories, and model the relations using graph Laplacian, which is employed as a regularization to a sparse formulation
  • Experimental results show that the user-centric social relations are helpful for sentiment classification of microblogging messages
  • Empirical evaluations demonstrate that our framework significantly outperforms the representative sentiment classification methods on two real-world datasets, and SANT achieves consistent performance for different sizes of training data, a useful feature for sentiment classification
Methods
  • We present empirical evaluation results to assess the effectiveness of our proposed framework, and answer the question: “Can social relations improve sentiment classification of microblogging messages?”.
  • The authors first present the finding of comparing SANT with the classical text-based sentiment classification methods, and with the models that incorporate social relations in sentiment classification.
  • In the first set of experiments, the authors use classification accuracy as the performance metric, and compare the proposed framework SANT with following text-based methods: LS Lasso MinCuts LexRatio SANT D10% D25% D50% D100% 0.670 (N.A.) 0.704 (N.A.)
Results
  • Empirical evaluations demonstrate that the framework significantly outperforms the representative sentiment classification methods on two real-world datasets, and SANT achieves consistent performance for different sizes of training data, a useful feature for sentiment classification.
Conclusion
  • CONCLUSIONS AND FUTURE WORK

    Different from texts in traditional media, microblogging texts are noisy, short, and embedded with social relations, which presents challenges to sentiment analysis.
  • The proposed method can utilize sentiment relations between messages to facilitate sentiment classification and effectively handle noisy Twitter data.
  • Experimental results show that the user-centric social relations are helpful for sentiment classification of microblogging messages.
  • Empirical evaluations demonstrate that the framework significantly outperforms the representative sentiment classification methods on two real-world datasets, and SANT achieves consistent performance for different sizes of training data, a useful feature for sentiment classification
Tables
  • Table1: Statistics of the Datasets
  • Table2: Sentiment Classification Accuracy on STS Dataset
  • Table3: Sentiment Classification Accuracy on OMD Dataset
Download tables as Excel
Related work
  • Recently, sentiment analysis on microblogging, which is considered to be an opinion-rich resource, has gained huge popularity and attracted researchers from many disciplines [3, 18, 20, 30]. Bollen et al [3] proposed to measure the sentiments on Twitter over time, and compared the correlation between sentiments and major events, including the stock market, crude oil prices, elections and Thanksgiving. Also, Kim et al [20] examined a tweet dataset about Michael Jackson’s death to gain insight into how emotion is expressed on Twitter. O’Connor et al [30] used sentiment analysis to automatically label the sentiments of tweets about politicians, and found strong correlation between the aggregated sentiment and the manually collected poll ratings.

    Sentiment classification has been studied for years on various text corpus, like newspaper articles [33], movie reviews [31], and product reviews [5, 11, 23]. The basic idea of the methods is to build a sophisticated feature space, which can effectively represent the sentiment status of the texts. Existing methods, which are designed for traditional i.i.d. text data, cannot effectively make use of the abundant social relation information contained in microblogging. Following the methods for traditional texts, there are some existing efforts in the community on the microblogging data. Alec et al [8] presented the results of machine learning algorithms for classifying the sentiments of Twitter messages using distant supervision. Barbosa and Feng [2] explored the linguistic characteristics of how tweets are written and the metainformation of words for sentiment classification. The ideas of the methods are consistent with traditional ones, ignoring the social relation information.
Funding
  • This work is, in part, supported by ONR (N000141110527) and (N000141010091)
Reference
  • R. Abelson. Whatever became of consistency theory? Personality and Social Psychology Bulletin, 1983.
    Google ScholarLocate open access versionFindings
  • L. Barbosa and J. Feng. Robust sentiment detection on twitter from biased and noisy data. In Proceedings of ACL, 2010.
    Google ScholarLocate open access versionFindings
  • J. Bollen, A. Pepe, and H. Mao. Modeling public mood and emotion: Twitter sentiment and socio-economic phenomena. CoRR, abs/0911.1583, 2009.
    Findings
  • F. Chung. Spectral graph theory. Number 92. Amer Mathematical Society, 1997.
    Google ScholarFindings
  • X. Ding and B. Liu. The utility of linguistic rules in opinion mining. In Proceedings of SIGIR, 2007.
    Google ScholarLocate open access versionFindings
  • J. Fowler and N. Christakis. The dynamic spread of happiness in a large social network. BMJ: British medical journal, 2008.
    Google ScholarFindings
  • J. Friedman, T. Hastie, and R. Tibshirani. The elements of statistical learning, 2008.
    Google ScholarFindings
  • A. Go, R. Bhayani, and L. Huang. Twitter sentiment classification using distant supervision. Technical Report, Stanford, 2009.
    Google ScholarFindings
  • Q. Gu and J. Han. Towards feature selection in network. In Proceedings of CIKM, 2011.
    Google ScholarLocate open access versionFindings
  • E. Hatfield, J. Cacioppo, and R. Rapson. Emotional contagion. Current Directions in Psychological Science, 1993.
    Google ScholarLocate open access versionFindings
  • M. Hu and B. Liu. Mining and summarizing customer reviews. In Proceedings of SIGKDD, 2004.
    Google ScholarLocate open access versionFindings
  • X. Hu and H. Liu. Text analytics in social media. Mining Text Data, pages 385–414, 2012.
    Google ScholarFindings
  • X. Hu, N. Sun, C. Zhang, and T.-S. Chua. Exploiting internal and external semantics for the clustering of short texts using world knowledge. In Proceedings of CIKM, pages 919–928, 2009.
    Google ScholarLocate open access versionFindings
  • X. Hu, L. Tang, and H. Liu. Enhancing accessibility of microblogging messages using semantic knowledge. In Proceedings of the 20th CIKM, 2011.
    Google ScholarLocate open access versionFindings
  • Y. Hu, A. John, D. Seligmann, and F. Wang. What were the tweets about? topical associations between public events and twitter feeds. ICWSM, 2012.
    Google ScholarLocate open access versionFindings
  • Y. Hu, A. John, F. Wang, and S. Kambhampati. Et-lda: Joint topic modeling for aligning events and their twitter feedback. In AAAI, 2012.
    Google ScholarLocate open access versionFindings
  • S. Ji and J. Ye. An accelerated gradient method for trace norm minimization. In ICML, 2009.
    Google ScholarLocate open access versionFindings
  • S. Kamvar and J. Harris. We feel fine and searching the emotional web. In Proceedings of WSDM, pages 117–126, 2011.
    Google ScholarLocate open access versionFindings
  • D. Keltner and G. Bonanno. A study of laughter and dissociation: Distinct correlates of laughter and smiling during bereavement. Journal of Personality and Social Psychology, page 687, 1997.
    Google ScholarLocate open access versionFindings
  • E. Kim, S. Gilbert, M. Edwards, and E. Graeff. Detecting sadness in 140 characters: Sentiment analysis of mourning michael jackson on twitter. 2009.
    Google ScholarFindings
  • H. Kwak, C. Lee, H. Park, and S. Moon. What is twitter, a social network or a news media? In Proceedings of WWW, 2010.
    Google ScholarLocate open access versionFindings
  • K. Lewis, M. Gonzalez, and J. Kaufman. Social selection and peer influence in an online social network. PNAS, pages 68–72, 2012.
    Google ScholarLocate open access versionFindings
  • B. Liu. Sentiment analysis and opinion mining. Synthesis Lectures on Human Language Technologies, pages 1–167, 2012.
    Google ScholarFindings
  • J. Liu, S. Ji, and J. Ye. Multi-task feature learning via efficient l 2, 1-norm minimization. In Proceedings of UAI, 2009.
    Google ScholarLocate open access versionFindings
  • P. Marsden and N. Friedkin. Network studies of social influence. Sociological Methods & Research, 1993.
    Google ScholarLocate open access versionFindings
  • M. McPherson, L. Smith-Lovin, and J. Cook. Birds of a feather: Homophily in social networks. Annual review of sociology, pages 415–444, 2001.
    Google ScholarLocate open access versionFindings
  • M. Miller, C. Sathi, D. Wiesenthal, J. Leskovec, and C. Potts. Sentiment flow through hyperlink networks. In Proceedings of ICWSM, 2011.
    Google ScholarLocate open access versionFindings
  • A. Mislove, S. Lehmann, Y. Ahn, J. Onnela, and J. Rosenquist. Pulse of the nation: Us mood throughout the day inferred from twitter. 2010.
    Google ScholarFindings
  • Y. Nesterov and I. Nesterov. Introductory lectures on convex optimization: A basic course. 2004.
    Google ScholarFindings
  • B. O Connor, R. Balasubramanyan, B. Routledge, and N. Smith. From tweets to polls: Linking text sentiment to public opinion time series. In Proceedings of ICWSM, 2010.
    Google ScholarLocate open access versionFindings
  • B. Pang and L. Lee. A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. In Proceedings of ACL, 2004.
    Google ScholarLocate open access versionFindings
  • B. Pang and L. Lee. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval, pages 1–135, 2008.
    Google ScholarLocate open access versionFindings
  • B. Pang, L. Lee, and S. Vaithyanathan. Thumbs up?: sentiment classification using machine learning techniques. In Proceedings of EMNLP, 2002.
    Google ScholarLocate open access versionFindings
  • D. Shamma, L. Kennedy, and E. Churchill. Tweet the debates: understanding community annotation of uncollected sources. In Proceedings of the first SIGMM workshop on Social media, pages 3–10. ACM, 2009.
    Google ScholarLocate open access versionFindings
  • M. Speriosu, N. Sudan, S. Upadhyay, and J. Baldridge. Twitter polarity classification with label propagation over lexical links and the follower graph. In Proceedings of the First Workshop on Unsupervised Learning in NLP, 2011.
    Google ScholarLocate open access versionFindings
  • C. Tan, L. Lee, J. Tang, L. Jiang, M. Zhou, and P. Li. User-level sentiment analysis incorporating social networks. In Proceedings of SIGKDD, 2011.
    Google ScholarLocate open access versionFindings
  • J. Tang and H. Liu. Feature selection with linked data in social media. In SDM, 2012.
    Google ScholarLocate open access versionFindings
  • J. Tang, X. Wang, H. Gao, X. Hu, and H. Liu. Enriching short texts representation in microblog for clustering. Frontiers of Computer Science.
    Google ScholarFindings
  • J. Wiebe, T. Wilson, and C. Cardie. Annotating expressions of opinions and emotions in language. Language Resources and Evaluation, 39:165–210, 2005.
    Google ScholarLocate open access versionFindings
  • T. Wilson, J. Wiebe, and P. Hoffmann. Recognizing contextual polarity in phrase-level sentiment analysis. In Proceedings of HLT and EMNLP, 2005.
    Google ScholarLocate open access versionFindings
  • X. Zhao, G. Li, M. Wang, J. Yuan, Z.-J. Zha, Z. Li, and T.-S. Chua. Integrating rich information for video recommendation with multi-task rank aggregation. In Proceedings of ACM MM, 2011.
    Google ScholarLocate open access versionFindings
Your rating :
0

 

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科