Analyzing Photos of Trump and Clinton in Media Coverage of the 2016 Election
We’re adding a new way to help you understand the different conversations happening in the media. We call it the “word space” chart. Out initial results indicate that the word space visualization can help users with limited knowledge of a topic find conversations that would otherwise be difficult to identify without deeper study of the text corpus.
We currently do most analysis and searching at the sentence level. We're switching to do everything at the story level on May 12, because that is what most people tell use they want. This will also help us save space and make things faster. This is a big change. Your current queries and topics will need to be updated after May 12 and will produce different results.
The Media Cloud team is actively looking to hire for two open positions.
This blog post summarizes our latest pass at investigating existing solutions for the second question: author detection in semi-structured web-based text. There are a few approaches we can pull from: using pattern matching, relying on structured metadata, or sourcing the job out to more complex algorithms and APIs.
In July 2017, internet companies and activists around the world came together for a “Day of Action” to protest the Federal Communications Commissions’ decision to rollback net neutrality protections. How has this activism affected both news media and public interest in this historically obscure issue? Using Google Trends and Media Cloud’s search frequency, we analyze the impact of the Day of Action on net neutrality awareness.
We present an unsupervised method that allows us to surface the main named-entities, i.e., people, locations, and organizations, discussed by the media in news articles on same-sex marriage. We follow an outlier detection approach to identify such entities of interest. Our initial exploration shows that the outlier named-entities, in a specific time period, provide useful initial knowledge that complements the information discovered based on popularity or topic detection methods.
We just released a new feature for the Topic Mapper tool that supports looking at how a word is used. This kind of investigation into use of a word in context can be very helpful to start to gain more insights than you can from a simple check of word frequencies. Here are a few examples to illustrate why this can be useful. Hopefully you find it as revealing as we have already!
The deadline for Standing Rock campsite residents to depart their campsites along the Missouri River occurred last Wednesday. The evacuation deadline passed at 2 pm MST, coincidently marking a two year effort to prevent the construction of the Dakota Access Pipeline (DAPL), a conduit spanning 1,172 miles with the purpose of transporting crude oil from North Dakota to Illinois. Representatives from approximately 300 of the 566 recognized Native American tribes in the United States actively participated at the Standing Rock Reservation in North Dakota since April of 2016.
Some years ago, journalist and activist, the late Dori Maynard posed a question to the Media Cloud team: Does sports media use different language to talk about black and white athletes? The question, Dori told us, came from basketball player Isaiah Thomas, who had observed that journalists often described black athletes as physically talented but talked about the intelligence of white athletes. While both descriptions are laudatory, they focus on different aspects of a player’s talents, and enforce long-standing racial stereotypes about intellect and physicality. Could Media Cloud, Dori wondered, put some numbers to these anecdotes?
In December 2012, a young girl was gruesomely gang raped in New Delhi, India. The method of the rape was particularly violent, involving insertions of a metal rod and irreparable intestinal damage. For the days following, Jyoti Singh went through emergency treatment in hospitals in India and Singapore, until finally succumbing to her injuries 13 days later.
In order to address the original question then of women’s issues in Indian English language press and how it may be influencing wider gender norms, I conducted a quantitative analysis of the news data and compared to the above behavior-change criteria.
A non-profit data journalism blog in India is playing a crucial role in better informing mainstream news content.
We have recently started looking into more topics around public health, which share these intertwined processes of creating and consuming knowledge and policy. Like traditional broadcast media, public health officials have traditionally been interested in distributing information from experts out to the masses. In the case of public health, the experts are scientists and doctors. But just as the internet has disrupted the flow of political information from political elites down to the crowds, it has also disrupted the flow of health information from scientists and doctors to the general public. Recently we’ve been looking at the topic of teen pregnancy because it provides a fascinating case study of a public health topic that is the center of a rich diversity of discussion in online media.
This post is the second in a series that will present work done by participants of the Media Cloud Summer Data Challenge this past summer.
When it comes to news coverage of abortion related topics, women are often left out of the picture. Instead, the visuals paired with abortion news stories favor contentious politics, and the men who run them.
In the one-thousand most linked to news stories on the topic of abortion in the media from October 1, 2014 to March 30, 2015, just 8.13 percent of 923 photos featured potential abortion patients. In a random sample of stories from that period, they made up just over six percent. So what did they feature?
This post is the first in a series that will present work done by participants of the Media Cloud Summer Data Challenge this past summer. This blogpost was written by Daniel Preotiuc-Pietro, Dean Fulgoni and Jordan Carpenter.
Although almost everyone agrees that some things are morally good and some things are morally bad, the specific form of these beliefs can differ throughout the population. What is egregious to one person: harming marginalized communities, banning sugary soft drinks, refusing to go to church, etc.; can be considered completely trivial or even be endorsed by someone else.
The Moral Foundations Theory [1,2,3] was developed to model and explain these differences. Under this theory, there are a finite number of basic, moral values that people can intuitively support, but not necessarily to the same extent across the population. As part of the Media Cloud Data Challenge, we thought this would be a perfect way to explore the extent to which the moral foundations are invoked in news discourse.
When we see these polarized network maps, it’s easy to think that the bridges between them offer some hope of escaping these echo chambers. But opposing sides don’t always follow or link to something for the same reason. Sometimes, opposing sides link to material to disagree with it or make straw-man arguments (Hargittai 2008). At such times, overlapping links can draw out the core disputes in a controversy, with what Zeynep Tufekci calls “hate-linking” (2014). To show how this happens, we examine how opposing sides linked to information sources in the Gamergate controversy.
Media Cloud fellow Rebecca Weiss is presenting a paper at the International Communications Association 2014 Conference, in the “Advances in Measurement and Methodology” track. The paper is titled “A Case Study in Computational Content Analysis: Comparisons of Sentiment Analysis Methods on News Media“.