Cordelia Ludden and Helena Simson, Tufts University; Sarah Radway, Harvard University; Daniel Votipka, Tufts University
The emergence of third-party services offering to manipulate Google PageRank results are of grave concern. In this work, we take steps to investigate this threat by observing changes in search rankings over time, to identify possible PageRank manipulation. We track changes in the order of results returned for these queries, and use both analysis methods (1) from cybersecurity-based anomaly detection and (2) based in sentiment analysis to determine features organizations can use to identify artificial PageRank manipulation. In this way, search engines can ensure they employ this knowledge to potentially protect against bad actors. As this is a work in progress, we present initial findings here, and discuss future steps forward for this work.
Open Access Media
USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.
