During this week, we will discuss how to measure positive and negative sentiment on social media.

Presentations

Nikolai is presenting:
Less than you think: Prevalence and predictors of fake news dissemination on Facebook
Andrew Guess, Jonathan Nagler, and Joshua Tucker (2019)

Readings

  1. Affective News: The Automated Coding of Sentiment in Political Texts
    Political Communication, 2012
    Lori Young and Stuart Soroka

  2. Estimating Geographic Subjective Well-being from Twitter: A Comparison of Dictionary and Data-driven Language Methods
    Proceedings of the National Academy of Sciences, 2020
    Kokil Jaidka, Salvatore Giorgi, H. Andrew Schwatz, Margaret L. Kern, Lyle H. Ungar, and Johannes C. Eichstaedt

  3. Tones from a Narrowing Race: Polling and Online Political Communication during the 2014 Scottish Referendum Campaign
    British Journal of Political Science, 2020
    Evelyne Brie and Yannick Dufresne
    Data from this article will be used in the lab

Additional applications of sentiment analysis (Optional):

  1. Experimental Evidence of Massive-scale Emotional Contagion through Social Networks
    Proceedings of the National Academy of Sciences, 2014
    Adam D. I. Kramer, Jamie E. Guillory, and Jeffrey T. Hancock

  2. Do Anti-Immigrant Laws Shape Public Sentiment? A Study of Arizona’s SB 1070 Using Twitter Data
    American Journal of Sociology, 2017
    René D. Flores

In the lab/lecture I will also mention the following additional articles:

  1. Measuring Emotion in Parliamentary Debates with Automated Textual Analysis
    PLoS One, 2016
    Ludovic Rheault, Kasper Beelen, Christopher Cochrane, and Graeme Hirst

  2. Diurnal and Seasonal Mood Vary with Work, Sleep, and Daylength Across Diverse Cultures
    Science, 2011
    Scott A. Golder and Michael W. Macy

Lab

In this lab, we will conduct sentiment analysis on data from the article by Brie and Dufresne (2020) (from the readings) by replicating their whole analysis from scratch using a variety of different sentiment dictionaries.

The R file for this lab can be found here: Sentiment_Analysis_Lab.R

Polling data and sentiment scores from the authors: PollData-ForRegression.csv

Tweets from the Better Together and Yes Scotland campaigns: Tones_Tweets.csv

AFINN sentiment dictionary: AFINN-111.txt