Sentiment analysis on evolving social streams: how self-report imbalances can help

By Pedro Calais Guerra, Wagner Meira Jr, Claire Cardie. 2014

43 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistical and Nonlinear Physics

In Signal Processing

Citations in the corpus

A Critical Review of Online Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2018, background): “We will review both recent work raising concerns about what can be legitimately inferred from existing social datasets [31, 35], as well as research that tries to quantify the limits of such data [10, 14, 19, 27].”
Discussion Graphs: Putting Social Media Analysis in Context (2014, background): “Given the many biases known to be present in social media (Calais Guerra, Meira, and Cardie 2014; Kıcıman 2012), validation of information inferred from social media is critical.”
Distilling the Outcomes of Personal Experiences: A Propensity-scored Analysis of Social Media (2017, background): “This ignores population and various selection biases [47, 52].”
Classification with class imbalance problem: A review (2015, background): “Many previous works such as sentiment analysis on Twitter media[148], live reactions on sports from Twitter [149], sentiment classification from social media [150] and sentiment analysis on online shopping review [151] reported class imbalanced problem does exist in such domain.”
On Unravelling Opinions of Issue Specific-Silent Users in Social Media (2016, background): “However, social media content is generated when users choose to self-report their thoughts (Kiciman 2012; Guerra, Meira, and Cardie 2014).”
Extracting Human Temporal Orientation from Facebook Language (2015, background): “Others utilize psychological knowledge about people, such as exploiting the human tendency to report more positive extreme feelings than negative in order to improve on sentiment analysis (Guerra et al., 2014).”