by Alessandra Maia Terra de Faria, Carlos Trucíos, and Marcelos Cantañeda de Araújo

Reviewed by Matheus Lucas Hebling

Find out what and how presidential candidates tweet and are tweeted.

 Introduction

This research aims to follow the tweets related to the three main presidential candidates according to the opinion polls available for the 2022 elections in Brazil.

Results

Followers

Daily tweets spanning from August 1st to August 31st were collected for each one of the three main candidates in the Brazilian presidential election. Tweets were collected from both candidates’ timelines and Twitter users mentioning the candidates, totalling more than 26 million tweets, the largest volume of monthly data obtained since the beginning of the survey. This increase coincides with the beginning of the electoral advertising period, which took place on August 16, 2022. Data were extracted through a Twitter API used exclusively for academic purposes and analyzed using R software.

The authors thank Twitter for the academic accounts granted to them.

Herein is the updated data (August versus July, data as of October 11th, 2022) of Twitter followers for each of the candidates.

  • Bolsonaro – from 8.6 up to 9.2 million (about a 7% increase in followers in comparison to the previous month)

  • Lula – from 4 up to 4.8 million ( about a 20% increase in followers in comparison to the previous month)

  • Ciro – from 1,4 million to 1.5 million (about a 7% increase in followers in comparison to the previous month)

 Candidates’ tweets

In Image 1, we report the number of tweets on the candidates’ timelines, among the three that were part of our survey: Lula, Ciro, and Bolsonaro, according to the frequency with which the candidates tweeted in August.

Image 1: Timelines

Unlike the months of June and July, in which candidate Lula was the one who tweeted more on his timeline, the month of August shows a greater interaction of candidate Ciro Gomes on the social network. Candidate Jair Bolsonaro, on the other hand, continues to be the one who tweets less on his timeline, a phenomenon observed since the beginning of our research.

Images 2 and 3 present the most frequent words in the candidates’ timeline tweets and the most frequent words in the candidates’ timeline tweets weighted by the inverse document frequency (TF-IDF), respectively.

Image 2: Most frequently used words in the candidates’ timeline.

The analysis of the most frequent words in the candidates’ timeline tweets (Image 2) allows us to present a dominant panorama of the subjects they deal with. In common in the three profiles, we find the terms “today” [“hoje”] and “Brazil”, in the case of the second, maintaining the pattern found until July. The difference arose in the mention of the word “today” by the three, in addition to the change in the term “people” [“povo”], previously mentioned frequently in the three profiles. Although the term “people” is prominent in Lula and Ciro, it is more frequent in Lula’s profile than in the second, and no longer appears in Bolsonaro’s profile, where the term “all” [“todos”] stands out. In the profiles of Lula and Ciro, the terms “Lula”, “today” and “people” are common. In Lula’s profile alone, the emphasis on the verbs “to do” [“fazer”] and “come back” [“voltar”] and the nouns “day” [“dia”] and “life” [“vida”], which denotes a continuity of the propositional character found until July, with the novelty of the term “life”, that emphasizes purpose. In Ciro’s profile, the concern to name the other two candidates remains, as observed since April. It is possible to highlight in the consolidated for the month of August, the mentions of terms like “income” [“renda”], “program” [“programa”], and “Brazilians” [“brasileiros”]. Finally, in Bolsonaro’s profile, it is possible to identify that the mention of amounts in reais (“r” ), “2022”, “08” and “reduction” [“redução”] is maintained, which is consolidated in the sense of the observed new mentions of the term “taxes” [“impostos”]. This is new concerning the month of July and confirms our intuition from the previous month that the reduction referred to this subject.

Image 3 TF-IDF by candidates’ timeline

In Image 3, the TF-IDF (term frequency-inverse document frequency) reflects the frequency of words in candidate timeline tweets that are infrequent for the three candidates overall. Thereby:

  • In Lula’s profile, the novelty in August is in the terms “folks” [“gente”], “go back” [“voltar”], “want” [“quero”], “Manaus”, “campaign” [“campanha”] and “Campina” (Manaus and Campina are regions that received visits from the candidate through his campaigning acts) . The emphasis that remained in June and July was the theme of “hunger” [“fome”], “rebuild”[“reconstruir”], and “together” [“juntos”].

  • Bolsonaro’s profile repeats the terms “reduction” [“redução”], and “drugs” [“drogas”], about what was found in July. The novelty appears in the terms “Jair”, “items” [“itens”], “after” [“depois”], “sanitation” [“saneamento”], “media” [“mídia”], “dictatorships” [“ditaduras”], “ton”, “liter” [“litro”] (of gasoline) and “academy” [“academia”].

  • In Ciro’s profile, mentions of the words “Ciro” and “giro” continued. The others that emerged in August were “minimum” [“mínimo”], “folks” [“gente”], “Suplicy” (for Eduardo Suplicy, city ​​councilor running for state deputy for PT in São Paulo), “adm”, “Paula”, “Ana”, “1,000” and “debates” (The mention of Ana Paula Matos refers to the vice in his campaign).

Tweets about the candidate

The total number of tweets mentioning each candidate is displayed in Image 4 and the daily evolution is in Image 5.

Next, in Image 4, we present, in descending order (from the most cited to the least cited), the total number of tweets that mentioned the name of each candidate surveyed in the month of August: Bolsonaro, Lula, and Ciro.

To collect the tweets mentioning the respective candidates, the words “Bolsonaro”, “Ciro” and “Lula” were used as search criteria. Tweets mentioning “Ciro Nogueira” were excluded from the analyzes referring to candidate Ciro.

Image 4: Number of tweets mentioning the candidates.

The volume of tweets about the candidates continues in the same order as in previous months: Bolsonaro, Lula, and, finally, Ciro. However, the increase in the volume of user interactions mentioning each of the candidates increased significantly in all cases:

  • The number of tweets mentioning Bolsonaro went from 8,351,515 to 13,455,826, representing an increase of 61% over the previous month.

  • The number of tweets mentioning Lula went from 5,663,521 to 10,189,718, representing an increase of 79% over the previous month.

  • Finally, the number of tweets mentioning Ciro went from 726,072 to 2,447,570, representing an increase of 237% over the previous month.

The daily evolution of tweets mentioning each candidate is shown in Image 5. Among the biggest highlights, there is the expressive increase of Ciro Gomes in the last week of August. Another highlight is the expressive increase in the number of tweets involving candidate Lula, exceeding, and by far, the number of tweets mentioning candidate Bolsonaro on August 25th and 26th. These days correspond to the day of each of the candidate’s interviews in Jornal Nacional, from Rede Globo de Televisão. ( Jornal Nacional is the flagship television newscast of TV Globo).

Image 5: Daily evolution of tweets mentioning the candidates.

Word clouds

Finally, we present below three-word clouds with, excluding stop words, the top 100 words used in the interactions of Twitter users in August. For better visualization, each candidate’s name was taken from its cloud.

A word cloud is a graphical representation of the most frequent words within a text or set of texts.

Next, we present three-word clouds, where each one corresponds to a candidate. It is important to point out that each candidate’s name was taken from its cloud, for better visualization of the associated words. It should also be noted that each cloud reflects the 100 most relevant words associated, excluding stop words, with each candidate in the interactions of Twitter users on the thirty-first day of August.

In text analysis, stop words are quite common words such as “and”, “from”, “the”, etc. These words are not useful for analysis and are often removed before analysis.

Image 6: Word cloud for Bolsonaro

Image 7: Word cloud for Lula

Image 8: Word cloud for Ciro

When analyzing the clouds, we share the first impression of each one:

  • Bolsonaro: there is a change in the foreground. Where previously “Brazil” appeared, we now see “Lula” in great prominence, followed by “president” [“president”], “interview” [“entrevista”], “government” [“governo”], “globe” [“globo”] and “about” [“sobre”].

  • Lula: in the foreground appear “president” [“presidente”], followed by “Brasil”, “Ciro” and “PT”; in the background “ex”, “vote” [“votar”], “now” [“agora”], “interview”, [“entrevista”], “about” [“sobre”] and “debate”.

  • Ciro: the trend of recent months remained in the foreground “Lula” and “Bolsonaro”, now the former appears even greater than the latter. In the background appears “vote” [“votar”], followed by “debate”, “Brazil”, “president” [“presidente”], and “Tebet” (the last mentioning Simone Tebet, also a candidate for the MDB).

Sentiment analysis

The sentiment of each tweet was constructed by identifying the sentiments of the basic units (the words) using the Oplexicon v3.0 and Sentilex dictionaries, from the LexiconPT Package. Thus, each word found in the dictionaries receives 1, -1, or 0 scores, depending on whether the feeling is positive, negative, or neutral, respectively. Words not found in the dictionaries also receive a 0 score. The values assigned to each word within the tweet were added up, and depending on the result positive, negative, or zero, the sentiment of the tweet is classified. In Image 9, feelings (Negative, Neutral, and Positive) are presented in percentages per candidate. It is possible to highlight a balance between the feelings expressed in the tweets of the three candidates. Such data will be monitored over time comparatively. This is a picture, a sentimental snapshot of August on Twitter.

When analyzing proportionally the number of tweets mentioning each candidate, candidate Lula had the highest percentage of tweets with negative sentiment (32.57%), and candidate Bolsonaro had the highest percentage of tweets with a positive sentiment (29.30%). Candidate Ciro has the highest percentage of neutral tweets (39.74%).

Image 9: Sentiments of tweets per candidate

Next, it will be possible to look at the word cloud of each candidate, separately, according to the feelings attributed to each tweet, in Images 10, 11, and 12. Words in pink appear in tweets rated as associated with positive feelings, words in blue appear in tweets rated as associated with negative feelings, and words in beige appear in tweets rated as neutral.

The word clouds are considered the 200 most frequent words.

Image 10: Word cloud Sentiments for Bolsonaro

Image 11: Word cloud Sentiments for Lula

Image 12: Word cloud Sentiments for Ciro

  • Bolsonaro: Tweets related to candidate Bolsonaro that were classified as associated with positive feelings are characterized by words such as “alive”, “re-elected”, “world” and “better” [“vivo”, “reeleito”, “mundo” e “melhor”]. Tweets classified as associated with negative feelings are characterized by words such as “vote”, “guy”, “corruption” and “convict” [ “votar”, “cara”, “corrupção” e “presidiário”]. Finally, tweets considered neutral highlight “president”, “Lula”, “newspaper*” and “Globo” [“presidente”, “Lula”, “jornal*” e “Globo”].

  • Lula: Tweets related to candidate Lula that were classified as associated with positive feelings are characterized by words such as “world”, “better”, “see” and “truth” [“mundo”, “melhor”, “ver” e “verdade”]. Tweets classified as negative are characterized by words such as “vote”, “corruption”, “ex” and “convict” [“votar”, “corrupção”, “ex” e “presidiário”]. Finally, tweets with neutral sentiment are mainly characterized by the terms “13”, “president” and “Bolsonaro” [“13”, “presidente” e “Bolsonaro”].

  • Ciro: Tweets related to candidate Ciro that were rated as associated with positive feelings are characterized by words such as “better”, “prepared”, “see” and “education” [“melhor”, “preparado”, “ver” e “educação”]. Tweets classified as negative are characterized by words such as “vote”, “go”, “Lula” and “guy” [“votar”, “vou”, “Lula” e “cara”]. Finally, tweets with neutral sentiment are characterized by words like “Bolsonaro”, “cruel” and “newspaper*”. [“Bolsonaro”, “cruel” e “jornal*”].

*The word “jornal” in Portuguese means newspaper and journal, but those mentions appeared in connection with the interviews in Jornal Nacional, the flagship television newscast of TV Globo.

Final comments

The presentation of this dataset aims to contribute to interpretations about the movement on Twitter of possible candidates in the 2022 elections, as well as about what is said about them in the interactions of users of the platform throughout the month of August, in comparison to what was found in July (https://bras-center.com/july-brazilian-presidential-candidates-on-twitter/), what was found in June (https://bras-center.com/june-brazilian-presidential-candidates-on-twitter/ ), what was found in May (https://bras-center.com/category/publications/vol3num1/ ) and what was found in April ( https://bras-center.com/brazilians-presidential-candidates-on-twitter-april-report/). This is ongoing research work and will be refined over the months leading up to the 2022 election.

Alessandra Maia Terra de Faria, Social Sciences Department at PUC-RIO / PPGCS – UFRRJ. E-mail: alessandramtf@puc-rio.br

Carlos Trucíos, Department of Statistics, University of Campinas. E-mail: ctrucios@unicamp.br

Marcelo Castañeda de Araujo, Department of Business/UFRJ.

Alessandra Maia Terra de Faria, Marcelo Castañeda de Araujo and Carlos Trucíos (2022) "August: Brazilian presidential candidates on Twitter". Brazilian Research and Studies Blog. ISSN 2701-4924. Vol. 3 Num. 1. available at: https://bras-center.com/august-brazilian-presidential-candidates-on-twitter/, accessed on: December 2, 2022.