Qualitative research provides methodological guidelines for observing and studying communities and cultures on online social media platforms. However, such methods demand considerable manual effort from researchers and may be overly focused and narrowed to certain online groups. In this work, we propose a complete solution to accelerate qualitative analysis of problematic online speech -- with a specific focus on opinions emerging from online communities -- by leveraging machine learning algorithms. First, we employ qualitative methods of deep observation for understanding problematic online speech. This initial qualitative study constructs an ontology of problematic speech, which contains social media postings annotated with their underlying opinions. The qualitative study also dynamically constructs the set of opinions, simultaneous with labeling the postings. Next, we collect a large dataset from three online social media platforms (Facebook, Twitter and Youtube) using keywords. Finally, we introduce an iterative data exploration procedure to augment the dataset. It alternates between a data sampler, which balances exploration and exploitation of unlabeled data, the automatic labeling of the sampled data, the manual inspection by the qualitative mapping team and, finally, the retraining of the automatic opinion classifier. We present both qualitative and quantitative results. First, we present detailed case studies of the dynamics of problematic speech in a far-right Facebook group, exemplifying its mutation from conservative to extreme. Next, we show that our method successfully learns from the initial qualitatively labeled and narrowly focused dataset, and constructs a larger dataset. Using the latter, we examine the dynamics of opinion emergence and co-occurrence, and we hint at some of the pathways through which extreme opinions creep into the mainstream online discourse.
Download