- For this research, I have applied techniques from complexity theory, especially information entropy, as well as network graph analysis and community detection algorithms to identify clusters of viral bots and cyborgs (human users who use software to automate and amplify their social posts) that differ from typical human users on Twitter and Facebook. I briefly explain these approaches below, so deep prior knowledge of these areas is not necessary. In addition to commercial bots focused on promoting click traffic, I discovered competing armies of pro-Trump and anti-Trump political bots and cyborgs. During August 2017, I found that anti-Trump bots were more successful than pro-Trump bots in spreading their messages. In contrast, during the NFL protest debates in September 2017, anti-NFL (and pro-Trump) bots and cyborgs achieved greater successes and virality than pro-NFL bots.
- Detecting social bots and identifying social botnet communities are extremely important in online social networks (OSNs). In this paper, we first construct a weighted signed Twitter network graph based on the behavioral similarity and trust values between the participants (i.e., OSN accounts) as weighted edges. The behavioral similarity is analyzed from the viewpoints of tweet-content similarity, shared URL similarity, interest similarity, and social interaction similarity for identifying similar types of behavior (malicious or not) among the participants in the Twitter network; whereas the participant’s trust value is determined by a random walk model. Next, we design two algorithms – Social Botnet Community Detection (SBCD) and Deep Autoencoder based SBCD (called DA-SBCD) – where the former detects social botnet communities of social bots with malicious behavioral similarity, while the latter reconstructs and detects social botnet communities more accurately in presence of different types of malicious activities. Finally, we evaluate the performance of proposed algorithms with the help of two Twitter datasets. Experimental results demonstrate the efficacy of our algorithms with better performance than existing schemes in terms of normalized mutual information (NMI), precision, recall and F-measure. More precisely, the DA-SBCD algorithm achieves about 90% precision and exhibits up to 8% improvement on NMI.
- Need to finish installing all the bits for TF, PT, and HF and see how well the model inference works
- Working on Chinese translation and topic extraction. Got most parts working on the Chinese translation, but need to figure out how to use split() on utf-8
- 10:00 meeting with Vadim. Cleaned up a lot of the data dictionary and started to look for how we can possibly have a reverse yaw
- 2:00 Meeting with Jason. Basically a blend of code walkthrough and demo. Seems pretty solid