Outlining the significance of the RightRelevance score/ranking since not familiar with what Buzzsumo, Klout, Traackr et al do.
The RightRelevance score of an expert/influencer for a TOPIC represents the authority within the topical community say for e.g. 'machine learning' of that influencer.
We dampen followers count, tweet count etc. noisy signals and lay much more focus on the topical network itself.
We're primarily graph based and perform a 2-level people rank:
1. Global to reduce a ~200M graph to ~3M (for now) globally ranked influencers (first level reduction, we don't expose this)
2. Per topic to find ranked influencers for every structured topic (~40K) in our system. This is accomplished via graph partitioning at scale.
This is more akin to google pagerank but for people (instead of links/webpages) with many important differences.
Points to note:
- Each influencer can be part of multiple topical communities and have a different rank/score within each. This is exposed in our apps via scored tags.
- Other, non structured, topics work via free-form search but the relevance may not be of the same quality. This can be seen by the score '10', which, probably poorly done, means we didn't find a community for the topic.
- Both our topics and graph are mined and built algorithmically at scale and increasing in number with higher quality with every iteration.
The RightRelevance score of an expert/influencer for a TOPIC represents the authority within the topical community say for e.g. 'machine learning' of that influencer.
We dampen followers count, tweet count etc. noisy signals and lay much more focus on the topical network itself.
We're primarily graph based and perform a 2-level people rank:
1. Global to reduce a ~200M graph to ~3M (for now) globally ranked influencers (first level reduction, we don't expose this)
2. Per topic to find ranked influencers for every structured topic (~40K) in our system. This is accomplished via graph partitioning at scale.
This is more akin to google pagerank but for people (instead of links/webpages) with many important differences.
Points to note:
- Each influencer can be part of multiple topical communities and have a different rank/score within each. This is exposed in our apps via scored tags.
- Other, non structured, topics work via free-form search but the relevance may not be of the same quality. This can be seen by the score '10', which, probably poorly done, means we didn't find a community for the topic.
- Both our topics and graph are mined and built algorithmically at scale and increasing in number with higher quality with every iteration.
About the Author
Vishal Mishra
CoFounder & CEO, RightRelevanceFormer SDE at Microsoft2002-2013
Studied at The University of Texas at Austin
Lives in San Francisco, CA
24.5k answer views763 this month