Date of Award
Honors Bachelor of Arts
Artificial intelligence and algorithms are increasingly becoming commonplace in crime-fighting efforts. For instance, predictive policing uses software to predetermine criminals and areas where crime is most likely to happen. Risk assessment software are employed in sentence determination and other courtroom decisions, and they are also being applied towards prison overpopulation by assessing which inmates can be released. Public opinion on the use of predictive software is divided: many police and state officials support it, crediting it with lowering crime rates and improving public safety. Others, however, have questioned its effectiveness, citing civil liberties concerns as well as the possibility of perpetuating systemic discrimination. According to the Prison Policy Initiative, over 2.3 million Americans were incarcerated in 2017 . Of this population, 60 per cent were made up of people of color. African-American men are disproportionately targeted by the U.S. judicial system; they are more likely to be stopped and frisked by police, as well as receive stiffer sentences than white men for the same crimes . In light of these facts, using algorithms and predictive methods to make decisions-especially ones that may affect the freedom of individuals-requires further study. Investigating the increasingly intertwined relationship between technology and human liberties can help develop a better understanding of how artificial intelligence can help make lives more efficient and the judicial system more transparent. The news media plays a significant role in shaping opinions on controversial issues. Articles and reports on predictive policing not only inform the public, but they also influence how people perceive the use of artificial intelligence in law enforcement, and ultimately how we, as citizens, want to be policed. This study evaluates the role of news media in shaping public opinion on two fronts: (a) the use of predictive analytics in the justice system, and (b) the integration of artificial intelligence in everyday life. Working with a corpus of articles from major journalistic outlets, we apply a qualitative methodology based on grounded theory to identify the key frames that govern media representation of predictive policing. This study makes the following contributions: - A survey of current predictive policing techniques, including hot spot analysis, regression methods, near-repeat, and spatiotemporal analysis - Application of grounded theory methods to a qualitative analysis of a corpus of 51 online articles on the U.S. criminal justice system's use of predictive software and algorithms - Identification of two frames most commonly adopted by elite journalists writing for national news outlets Two dominant frames were identified from a corpus of 51 articles: fear of the future and fear of the past. The first frame elaborates on the potential consequences of implementing predictive algorithms in policing efforts, using specific examples to emphasize the difficulty of removing bias from software systems and the likelihood of perpetuating racial discrimination. The second frame argues that using data effectively can help combat rising crime rates, especially in metropolitan areas like Chicago and New York City. It bolsters its claim by attributing the ability of using predictive analytics to forecast crime as well as national threats before they happen - it focuses on preventing crime as opposed to combating it.
Cheng, Kar Mun, "Predictive Analytics in the Criminal Justice System: Media Depictions and Framing" (2018). Honors Program Theses. 62.
Kar Mun Cheng