SONAlysis since 1936 with R and Python
State of the Nation Addresses since 1936
Tomorrow, the President will be delivering his fourth State of the Nation Address (SONA). This morning, I decided to do some text analysis (more like frequency) on past SONAs (http://www.gov.ph/past-sona-speeches/). Here, I followed some keywords (that I chose) within each of the SONA given in the past years (from 1936-2012). I used both Filipino and English words in tracking said keywords, e.g. (“poverty” and “kahirapan”) or (“economy” and “ekonomiya”). The x-axis represents the years when the SONAs were given, while the y-axis represents the frequencies of the chosen words. The word frequencies are normalized across presidents.
Since I have not really looked into the individual speeches, I have opted to not give any political interpretations on the trends. I hope to refine the analysis some more with the help of my more politically inclined friends who have intuition on the various states of our nation.
keywords: development, economy, population, health, education, poverty, infrastructure
Below, I have plotted the comparison and commonality clouds of PNoy’s first three SONAs. I used R to generate said clouds. The commonality cloud shows the top words shared across his three speeches while the comparison cloud compares the frequencies of words across his speeches (in Filipino).
Same thing for the image below. Here, I used Python to restructure and concatenate Pres Arroyo’s (nine in total) and Pres Aquino’s speeches (3 in total). Note that for this analysis, I used the English (translated) version of PNoy’s three speeches. Just like in the above, I constructed the comparison and commonality clouds of the concatenated speeches.
Again, since I have not really looked into the individual speeches, I have opted to not give any political interpretations on the trends.
More word clouds from our last three presidents
ERAP
GMA
NOY-NOY
I have done some more text analyses, but it’s already running late (1:12AM). I’ll try to update this post ASAP.
I like the results of the clouds from arroyo!
LikeLike
In other words, not much substance in PNOY’s speeches!
LikeLike