Services

Data-capture

We help you to get and organize information from public data or different websites with scrapping.

Data-cleaning

We structure databases with information from multiple databases in multiple formats. Organization of information and standardization of variables.

Visualization apps

We create public data visualization applications so that your users can know and explore databases. We use the latest technologies in data visualization to communicate information.

Algorithms

We implement artificial intelligence algorithms to facilitate your work with data, from predictive algorithms to pattern recognition.

Web specials

We develop interactive web specials based on data. The specials have different visual components to guide your readers. See examples of our specials.

About us

Datasketch is a digital platform of investigative and data journalism. Our portal allows journalists, data scientists, social scientists and citizens in general to learn and consult on data visualizations, tools, software and in-depth research on various short-term issues. We have free data tools and different projects to bridge the gap between data and citizenship that facilitates the democratization of knowledge and a critical review of social realities based on information contrasts.

Our team

Juan Pablo Marín

Electronic engineer with a master's degree in computational statistics. Expert in data science with applications in multiple areas such as economics, hydrology and journalism.

Camila Achuri

Statistics and expert in R programming language. She has developed various applications of data visualization in mobility and open data subjects.

Juliana Galvis

Politologist and candidate for a Master in Digital Humanities. She is currently leading the development of the Who Is database, as well as supporting journalistic research and the creation of databases.

David Daza

Bachelor of Electronics. Expert in development of applications and websites with emphasis on data journalism and content management of multiple databases.

Verónica Toro

Anthropologist and researcher. Responsible for the management and organization of the data-community in Colombia and Latin America and provide support in journalistic investigations and the creation of databases.

Andrea Cervera

Journalist responsible for writing articles, provide investigative support and community manager.

Ana Hernández

Mathematician and expert in R programming language. She has collaborated for various projects such as Infraestructura Visible and in the development of visualization tools.

Contact

More than 70.000 words to hate Trump

March 03, 2017

What do countries feel towards the US president? Datasketch discovered it after analyzing nearly 60.000 headlines.

 

Lee la versión en español aquí.

 

The Trump phenomenon has shaken politics, international relations and the way the media, especially in the United States, relate to power.

 

The many criticisms that Trump has received in various newspapers, blogs or tv programs, such as Saturday Night Live, imply that the media do not like the new president.

 

To verify the truth of this statement, in Datasketch we did an analysis of the positive or negative feelings that reflect 153 media in their headlines when they talk about Trump. (You may want to read: Trump isn't that different...)

 

To do this, we used the tool Twingly, which collects information from various sources, news or blogs and classifies them according to language, keywords, URL or different tags. This allows you to explore digital content in a more structured way. In short, it is a Booking that instead of helping you find a hotel, allows you to capture text in articles from the blogosphere.

 

We used Twingly to get all the headlines published in Trump's first month as president: from the 20th of January until February 24. In total, we obtained 59.633 headlines. From those, we were able to connect 26.252 headlines with a specific state, according to its hostname.

 

Once we had this information, we did an analysis of feelings by exploring the words in those headlines and relating them to the feeling they represent according to a lexicon, a dictionary of words. This lexicon does not analyze context but the character of each word independently.

 

Thus, we knew whether a particular word was positive or negative and we could then analyze what feeling a news agency or a country had towards Trump.

 

The conclusion? Out of the 36 countries analyzed, only nine have "positive feelings" towards Trump. The remaining 27 publish content in which negative words are used to refer to the president or his political decisions.

 

Obviously, the US is the country that has a more negative feeling towards Trump, with 58.316 words. It's followed by Israel (2.271) and Australia (2.105).

 

The most used negative word is "ban",  it appears 45.642 times in the headlines. The most positive? "Pick", which appears 36.473 times.

 

If we look at what headlines refer to these words we see how the media in each country strongly criticized the executive orders signed by the president to build the wall with Mexico or the Muslim ban.

 

What happens in the US alone? Of the 50 states, we were able to analyze the headlines published by digital media in 27 of them.

 


According to the results, 25 out of the 27 states have a negative feeling towards Trump. There's no single state in which Trump won the election which media has a positive feeling towards him.

 

Get your own conclusions by playing with the different variables in the following visualization.

 

 

María Isabel Magaña

Journalist, Master in Investigative Journalism and #DataViz. Thus, I see data everywhere. Promoting transparency through queremosdatos.co

Diego Trujillo

Mathematician and data scientist