Characterizing debate performance via aggregated twitter sentiment

By Nicholas A. Diakopoulos, David A. Shamma. International Conference on Human Factors in Computing Systems, 2010

534 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/8b6d3359f61299db648e1b98efb41bf0d56bf912

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Statistical and Nonlinear Physics

Citations in the corpus

Crowdsourced Databases: Query Processing with People (2011, background): “As mentioned in Section 3, Qurk’s components communicate asynchronously.”
Political Communication and Influence through Microblogging--An Empirical Analysis of Sentiment in Twitter Messages and Retweet Behavior (2012, unknown): “Other works, such as studies by Diakopoulos and Shamma [10], and Shamma et al.”
Predicting the Political Alignment of Twitter Users (2011, background): “The machine learning apparatus outlined above, paired with sentiment analysis techniques, could supplement traditional phone-based opinion surveys by allowing political campaigns to monitor public opinion regarding specific candidates and issues among users in their voting base [40].”
Contextual semantics for sentiment analysis of Twitter (2016, methodology): “The STS-Gold dataset contains random tweets, with no particular topic focus, whereas OMD and HCR consist of tweets that discuss specific topics, and thus the contextual semantics extracted by SentiCircle are probably more representative in these datasets than in STS-Gold.”
Sentiment in Twitter events (2011, methodology): “The time series method used on the resulting data was able to predict not only the outcome of the debate but also particular points of interest during the debate that triggered emotions (Diakopoulos & Shamma, 2010).”
Characterizing the 2016 Russian IRA influence campaign (2018, background): “…many studies, including the past four U.S. Presidential elections Adamic and Glance (2005); Bekafigo and McBride (2013); Carlisle and Patton (2013); Diakopoulos and Shamma (2010); DiGrazia et al. (2013), and other countries like Australia Bruns and Burgess (2011); Gibson and McAllister (2006), and…”
On Using Twitter to Monitor Political Sentiment and Predict Election Results (2011, methodology): “An example is work by Diakopou-los and Shamma who characterised the 2008 US presidential debate in terms of Twitter sentiment (Diakopoulos and Shamma, 2010).”
Evaluation Datasets for Twitter Sentiment Analysis: A survey and a new dataset, the STS-Gold (2013, methodology): “The authors in [6] reported an inter-annotator agreement of 0.”
Twitinfo: aggregating and visualizing microblogs for event exploration (2011, background): “Diakopoulous and Shamma did inspirational work in this vein, demonstrating the use of timeline analytics to explore the 2008 Presidential debates through Twitter sentiment [6].”
Classifying sentiment in microblogs: is brevity an advantage? (2010, methodology): “Diakapolous and Shamma used manual annotations to characterize the sentiment reactions to various issues in a political debate [5].”
Motivations for sharing information and social support in social media: A comparative analysis of Facebook, Twitter, Delicious, YouTube, and Flickr (2015, methodology): “Amazon MTurk has been frequently used to collect data for social media research (e.g., Asur & Huberman, 2010; Diakopoulos & Shamma, 2010; Shah & Pomerantz, 2010; Nichols, Zhou,Yang, Kang, & Sun, 2013).”
Datafication, dataism and dataveillance: Big Data between scientific paradigm and ideology (2014, background): “…2010); Twitter has also been termed a “sentiment detector” of people’s political predilections (O’Connor et al. 2010) and a tool that helps understand the “dynamics of sentiment” by analyzing twitterers’ reactions to a specific video fragment (Diakopoulos and Shamma 2010; Bollen, Mao and Pepe 2010.”
Analyzing the Digital Traces of Political Manipulation: The 2016 Russian Interference Twitter Campaign (2018, background): “The use of digital media for political discussions during presidential elections was examined by many studies, including the past four U.S. Presidential elections [1, 8, 12, 20, 21], and other countries like Australia [11, 29], and Norway [24].”
Truthy: mapping the spread of astroturf in microblog streams (2010, methodology): “Similar techniques have been applied to infer relationships between media events such as presidential debates and affective responses among social media users [15].”
Detecting and Tracking Political Abuse in Social Media (2011, methodology): “Similar techniques have been applied to infer relationships between media events such as presidential debates and affective responses among social media users (Diakopoulos and Shamma 2010).”
Cybercrime detection in online communications: The experimental case of cyberbullying detection in the Twitter network (2016, unknown): “Generally the tweets are labeled via human coding (Dadvar & De Jong, 2012; Diakopoulos & Shamma, 2010; Ghahramani, 2015; Gokulakrishnan, Priyanthan, Ragavan, Prasath, & Perera, 2012; Myslín, Zhu, Chapman, & Conway, 2013; Paul, Dredze, & Broniatowski, 2014; Prieto, Matos, Alvarez, Cacheda, &…”