Alexandre Trilla, PhD - Data Scientist |

Blog

-- Thoughts on data analysis, software development and innovation management. Comments are welcome

Spanish Government presidential candidates face-off analytics

15-Nov-2011

This post is in line with a recent article that presents a novel application to signal the polarity of opinions in Twitter posts, see this piece of news published by Universidad de Alicante. The original work is centred on the face-off debate between Rajoy and Rubalcaba, the two main candidates for the Spanish Government presidential election that will take place next Sunday. I here reproduce a similar experiment with the default configuration of EmoLib, which is grounded on a centroid-based classifier representing the words' emotional dimensions in the circumplex, but with the transcription of the whole debate, which is available for the two candidates: Rajoy, on behalf of the PP, and Rubalcaba, on behalf of the PSOE. What follows is a table that shows some linguistic statistics regarding their speeches (bearing in mind that they spoke the same amount of time):

Feature	Rajoy (PP)	Rubalcaba (PSOE)
Total paragraphs	97	112
Positive paragraphs	32	40
Neutral paragraphs	46	56
Negative paragraphs	19	16
Total unigrams	8885	8859
Total bigrams	8788	8747
Unigram vocabulary	2207	2194
Bigram vocabulary	6133	5933

In contrast to the original article where only positive and negative tags were provided, EmoLib allows a more granular analysis with the additional "neutral" label, which lies in between the opposing extreme positive and negative labels. According to the statistics, note that both candidates have a similar speaking style. Perhaps Rubalcaba is more prone to expose his ideas incrementally while Rajoy prefers to put them forward at once, since the former has articulated 15 paragraphs more than the latter in the same amount of time. Anyhow, the richness of the vocabulary employed is similar (taken for the rate between the size of the vocabulary and the total amount of spoken words). Maybe what is most surprising is that the affective figures delivered by this study end up being contrary to the original ones, since Rajoy spoke positively 32.99% of the time while Rubalcaba did it a 35.71%. The rates continue being more of less comparable, but the trend is inverted wrt what has been originally published.