Bridging the Divide in Democratic Engagement: Studying Conversation Patterns in Advantaged and Disadvantaged Communities

The Internet offers opportunities for informal deliberation, and civic and civil engagement. However, social inequalities have traditionally meant that some communities, where there is a concentration of poverty, are both less likely to exhibit these democratic behaviors and less likely to benefit from any additional boost as a result of technology use. We argue that some new technologies afford opportunities for communication that bridge this divide. Using temporal topic modeling, we compare informal conversational activity that takes place online in communities of high and low poverty. Our analysis is based on data collected through i-Neighbors, a community website that provides neighborhood discussion forums. To test our hypotheses, we designed a novel time series segmentation algorithm that is driven by topic dynamics. We embed an LDA algorithm in a segmentation strategy and develop an approach to compare and contrast the resulting topic models underlying time series segments. We examine the adoption of i-Neighbors by poverty level, and apply our algorithm to six neighborhoods (three economically advantaged and three economically disadvantaged) and evaluate differences in conversations for statistical significance. Our findings suggest that social technologies may afford opportunities for democratic engagement in contexts that are otherwise less likely to support opportunities for deliberation and participatory democracy.