Media capture, captured: a new computational methodology to measure deteriorating media freedom

The media are under increasing pressure by states to adopt a regime-friendly editorial line in many countries globally, raising the importance of understanding the conditions of successful and failed media capture. Unfortunately, the standard measurement of media capture - annual expert surveys - neither distinguishes between outlets nor offers the needed resolution to assess, e.g., the immediate impact of a new gag law. To remedy these shortcomings, we develop a computational measurement of media capture based on a comparison of nominally independent outlets and regime-owned outlets regarding media agenda and tone when referring to the regime. By relying on two unsupervised measurement methods - topic modelling and sentiment classification - the new method can assess the loss of editorial independence at the level of individual outlets on a monthly or even weekly basis. The methodology is validated by applying it to recent data from Nicaragua. There the two-pronged approach shows how outlets respond differently to regime pressure. While there still are limitations to consider, if further editorial aspects of media capture such as issue framing are added to the methodology, it has the potential of transforming the future study of media capture.