Classifying Land Type from Satellite Imagery

 Posted on April 15, 2019  |  8 minutes  |  1524 words  |  

Introduction: Can we Classify Land Types using R? A few weeks ago I was looking into what sort of statistics exist on changing land types. I couldn’t find much else besides the CORINE land cover program, which is updated every 6 years. At the same time I stumbled across a fantastic book on using R for just this sort of analysis. [Read More]

What Can We Learn From Maltese Property Listings?

 Posted on March 20, 2019  |  14 minutes  |  2830 words  |  

Introduction I suppose a defining feature of being in your mid twenties is that you find progressively more of your small talk having to do with properties: how big they should be, which floor negates the value added by a lift, and even, when alternate conversation seems especially hard to conjure, the benefits of using one type of grout as opposed to another. Often during such conversations, I found myself wondering how much value can be extracted by an in-depth analysis. [Read More]

How And What Local Politicians Tweet

 Posted on November 13, 2018  |  9 minutes  |  1847 words  |  Charles Mercieca

Introduction: Political Tweets Politics has always been concerned with using any available method of mass media to disseminate its message, and social media is no exception. In Malta, the most popular social media sites, by share of their usage are, according to a May 2018 Misco survey: Facebook (87% of the population) Google+ (50%) YouTube (46%) Instagram (24%) Twitter (12%) I’ve yet to come across anyone who actually uses Google+ regularly, so those answers are probably people who just have an account. [Read More]

Text Mining Local News (Part 2)

 Posted on October 28, 2018  |  3 minutes  |  581 words  |  Charles Mercieca

Taking it one step past Part 1: But what’s really in the news? Besides answering questions like the frequency of how much individual publishers post, what distinct word or word pairs they write most about and the sentiment of their writing, text mining allows us to go one step further. If we set off from the starting point that each news article is a mixture of topics, and that each topic is in turn a mixture of words, we can measure the relative proportion in coverage one publisher devoted to topic A versus topic B. [Read More]

Text Mining Local News (Part 1)

 Posted on September 24, 2018  |  13 minutes  |  2769 words  |  Charles Mercieca

Introduction: Why Text Mine the Local News? Media ‘slant’ is a fascinating topic. Ask anyone who reads the news, and they’ll probably have a reason for choosing one media source over another. Invariably, that reason often turns out to be because, according to them, the one they read isn’t biased and all the others are. The starting point of this post was an attempt to recreate this graph for the local news context. [Read More]