The Pulse of Public Opinion: Using Twitter Data to Analyze Public Perception of Reform in El Salvador

Seabold, Skipper; Rutherford, Alex; Backer, Olivia De; Coppola, Andrea

doi:10.1596/1813-9450-7399

Cited by 5 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The preliminary evidence of this research suggest a methodology for an understanding of the main references to which the economic policy debate carried out throug social media relies on. In line with previous literature, our results suggest that the integration of text mining techniques with Twitter data has a great potential to add knowledge to social science (Chang, Chu, 2013;Rill et al, 2014;Seabold et al, 2015;. For our future research directions, we plan to reduce the set of tweets at only georeferenced tweets to focus these trends across countries and understand how these trends reflect the economic cycle.…”

Section: Preliminary Resultssupporting

confidence: 75%

“…To identify the semantic orientation of each line of text downloaded from Twitter we have adapted the functions of the "sentimentr" package developed by Rinker (2017) which uses a dictionary-based approach, i.e. based on a predefined polarized word list.…”

Section: Methodsmentioning

confidence: 99%

“…In fact tweets have a reliable timestamp and for that they can be analyzed from a time perspective and are accessible to researchers, unlike most social networking sites (Fujiwara et al, 2021). For these reasons, Twitter has found many applications among social scientists for many different purposes as detecting tourism preferences (Chang, Chu, 2013), analysing political trends (Rill et al, 2014, Seabold et al, 2015, or studying socio-economic problems .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

5th International Conference on Advanced Research Methods and Analytics (CARMA 2023)

2023

View full text Add to dashboard Cite

The development of the Internet and Big Data information sources is driving new and increasingly interdisciplinary research methods in economics and the social sciences. The 5th International Conference on Advanced Research Methods and Analytics (CARMA) is an excellent forum for researchers and practitioners to exchange ideas and advances on how emerging research methods and sources are applied to different fields of social sciences as well as to discuss current and future challenges.

show abstract

Section: Preliminary Resultssupporting

confidence: 75%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

5th International Conference on Advanced Research Methods and Analytics (CARMA 2023)

2023

View full text Add to dashboard Cite

show abstract

“…Yazdani and Manovich (2015) use Twitter images to predict socio-economic characteristics. Seabold et al (2015) use Twitter data to analyze public perception of the 2011 reform to the propane gas subsidy in El Salvador. Usherwood and Wright (2017) monitored the three main groups that made extensive use of social media during the UK European Union membership referendum (Brexit referendum).…”

Section: ! Big Data In Social Sciencesmentioning

confidence: 99%

What matters most to people around the world? Retrieving Better Life Index priorities on Twitter

Resce

Maynard

2018

Technological Forecasting and Social Change

View full text Add to dashboard Cite

Better Life Index (BLI), the measure of well-being proposed by the OECD, contains many metrics, which enable it to include a detailed overview of the social, economic, and environmental performances of different countries. However, this also increases the difficulty in evaluating the big picture. In order to overcome this, many composite BLI procedures have been proposed, but none of them takes into account societal priorities in the aggregation. One of the reasons for this is that at the moment there is no representative survey about the relative priorities of the BLI topics for each country. Using these priorities could help to design Composite Indices that better reflect the needs of the people. The largest collection of information about society is found in social media such as Twitter. This paper proposes a composite BLI based on the weighted average of the national performances in each dimension of the BLI, using the relative importance that the topics have on Twitter as weights. The idea is that the aggregate of millions of tweets may provide a representation of the priorities (the relative appreciations) among the eleven topics of the BLI, both at a general level and at a country-specific level. By combining topic performances and related Twitter trends, we produce new evidences about the relations between people's priorities and policy makers' activity in the BLI framework.1 The metrics are: dwellings without basic facilities, housing expenditure, rooms per person, household net adjusted disposable income, household net financial wealth, employment rate, job security, long-term unemployment rate, personal earnings, quality of support network, educational attainment, student skills, years in education, air pollution, water quality, consultation on rule-making, voter turnout, life expectancy, selfreported health, life satisfaction, assault rate, homicide rate, employees working very long hours, and time devoted to leisure and personal care. 2 www.oecdbetterlifeindex.org

show abstract

Section: Introductionmentioning

confidence: 99%

Assessing the spread of Keynesian ideas in the economic policy debate: a Text Mining approach on Twitter

Resce,

Perfetto,

Rancan

2023

5th International Conference on Advanced Research Methods and Analytics (CARMA 2023)

View full text Add to dashboard Cite

This paper proposes a methodology for examining the presence of Keynesian ideas in the economic debate. To this aim we use Twitter as a source of data to monitor the debate in real time. We quantify the presence of Keynesian and anti-Keynesian thought in tweets about the economy and we qualify the emotional tone of these tweets. Our preliminary results show that the 20 per-cent of total English tweets about #economy contain words related to Keynes while about 8 per- cent contain words referring to anti-Keynesian policies. The monthly analysis of the tweets shows a certain heterogeneity. The distribution of Keynes-related tweets is much more uneven than the distribution of anti-keynesian tweets. Our evidence suggests that the methodology we applied to understand how much of the Keynesian thought is still around in the economic debate can be promising. The next step will be to focus on georeferenced tweets to detect heterogenity across countries and to understand how country-level trends reflect the economy cycle. This study still has some limitations that will be faced in future research such as the classification of topics and the focus on English texts for the moment.

show abstract

The Pulse of Public Opinion: Using Twitter Data to Analyze Public Perception of Reform in El Salvador

Cited by 5 publications

References 20 publications

5th International Conference on Advanced Research Methods and Analytics (CARMA 2023)

5th International Conference on Advanced Research Methods and Analytics (CARMA 2023)

What matters most to people around the world? Retrieving Better Life Index priorities on Twitter

Assessing the spread of Keynesian ideas in the economic policy debate: a Text Mining approach on Twitter

Contact Info

Product

Resources

About