Cronycle Topics & Influencer Communities

Reading Time: 2 minutes

Cronycle is an information workflow application powered by Right Relevance (subsidiary of Cronycle), which is a topical information search and relevance platform.

Topics and Influencers (per topic) form the backbone of the search and relevance technology.

  1. Topics (over 50 thousand) including metadata like related topics & semantics like synonyms, acronyms.
  2. Topical influencers (over 2.5M) with score and rank.

Topics are identified by algorithmically mining over 10M unstructured documents on the web and leveraging Wikipedia and Right Relevance topical graph neighborhood techniques. Relationships and semantics are derived from this process with manual corrections and injections for the last mile.

Topical Influencers mining is fully algorithmic and primarily graph based. The methodology leverages ML, semantic analysis and NLP on unstructured data at scale and involves a 2-level proprietary people rank (custom page rank for social graphs):

Stage 1. Global PR to reduce a ~300M nodes graph to ~6M (for now) globally ranked influencers. This is a first level reduction and we don’t expose the scores. It doesn’t have topical context.

Stage 2. Graph partitioning of the ~6M connected nodes from stage 1 across our ~50K structured topic space using unstructured data assigned to each node. This leads to ~50K per topic sub-graphs, where a secondary PR is applied to determine the topic score for each node in each topical sub-graph. This secondary PR score is normalized to calculate the Right Relevance topic score and rank influencers for every structured topic in our platform. 

Our custom PR algorithm is derived from google pagerank but is specialized for social graphs (instead of links/webpages) with many important differences applicable to social networks.

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. This measure of influence per topic is termed as ‘topical influence’ and the topical communities formed are termed as “Tribes“.

Once we have the scored and ranked influencers’ community for a particular topic (e.g. machine learning, behavioral science, big data, emergency medicine, oil and gas, angularjs,  social media marketing etc.) we mine the web for content. The numeric influence from topics and influencers is inductively applied to this content for measuring relevance and forms a critical part of the search. We download ~600K articles daily from ~2M websites every month. Topical content and information are available in the form of articles, videos and conversations.

Points to note:

  • We dampen followers count, tweet count etc. noisy signals and lay much more focus on the topical network itself.
  • Each influencer can be part of multiple topical sub-graphs aka communities and have a different score, and rank, 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 topics and influencer graphs are mined and built algorithmically at scale with ever-increasing quality after every iteration.

The Death of Klout is not the end for Influencer Models

Reading Time: 3 minutes

Amongst the General Data Protection Regulation’s (GDPR) first casualties, Klout stands out for the lack of sorrow at its demise. The premise was simple enough: distilling users presence across multiple social media platforms to give a single score. The (almost always) two digit number bears an eerie resemblance to the rather vague and sensationalist descriptions of China’s social credit scheme, Sesame Credit – albeit several years ahead of the Communist Party’s alleged plans.

The premise was flawed for several reasons. For one, there were concerns about the ethics of an opaque system for measuring social media influence, not least one boiling users’ influence down to a couple of numbers. Secondly, and perhaps more pressingly, Klout’s model was (for want of a better word), useless. Rather than showing anything meaningful about social media influencers, it did little more than aggregate scores (often woefully poorly). When a social media score did little more than  Even worse were its descriptions of influencers areas of specialism: as The Drum pointed out, Klout’s view of Pope Francis portrayed him as both an expert theologian and a leader on Marxism, warfare, and Miss Universe. Such profiles did not fill the world of marketing and PR with great hope for Klout, which is winding down on May 25th (the same day as GDPR).

Whilst the regulations undoubtedly played a role in the downfall of Klout (a service which almost certainly didn’t play by regulations in terms of data collection and processing), its failure to make a meaningful service was almost certainly at its core. That’s not to say that studying influencers is worthless for marketers, journalists, and communication professionals – just that smarter ways of studying influence are necessary.

One of these comes from Cronycle’s service. In addition to using Twitter data and network analysis to produce our Insight Reports. Cronycle keeps tabs on influencers across multiple topics through our Right Relevance platform across dozens of topics. Rather than giving users a single score, they receive scores for individual topics and sub-topics – this more granular approach is more valuable since it allows users to narrow down on the specific expert or influencer they want. It also builds up links with related influencers, creating networks which reflect underlying similarities and ties.

An image of top influencers on the topic of GDPR. The sliders on the right allow for users to narrow down on the group they are particularly interested in.

The service extends beyond Klout’s focus on numbers, though. At the broader end of the scale, Croncyle’s service gives a dashboard allowing you to search through topics, compare trending hashtags, look at the top influencers and domains, and see related topics.

The Cronycle Influencer and Topic dashboard for AI

Cronycle users can also search through articles by top influencers on their areas of speciality (as well as through related topics), giving both the tweets by the influencers and their articles. Domain searches are another feature, giving a list of top topics and top influencers for specific sites.

The final aspect is Topic Intel, which allows users to compare a single subject across time – an equally important comparison to that between different subjects.

Topic intel for AI and Machine Learning

Users can easily find how the top spots have changed – or not – for their subjects, as sorted by retweets or mentions (all Twitter activity).

Klout may be dying, but the influencer model is by no means moribund. Holistic approaches, like Cronycle’s, build on Klout’s work of showing influence through a numeric system but seriously ramping up the extra information required to make that useful.

Are you an influencer?

Reading Time: 2 minutes

This week we rolled out a new feature update which allows you to identify who is an influencer

Influencers. The word seems to be thrown around so much nowadays, with the likes of influencer marketing as a strategy or celebrities like the Kardashians supposedly impacting Snapchat’s user base and uninstalls. As described by IMB,

An influencer is an individual who has the power to affect purchase decisions of others because of his/her authority, knowledge, position or relationship with his/her audience. An individual who has a following in a particular niche, which they actively engage with. The size of the following depends on the size of the niche.”

How does an influencer enhance my content curation experience? As you know, we recently rolled out “topics” which are curated by content from top influencers. We have taken this experience one step further to be more transparent with you about who those influencers are. In your advanced settings, you now have the ability to dictate whether you want that particular feed to be from the top 20, top 100 or a custom score range of influencers. This short video shows you how and where you can find this functionality.

 

In addition, if you are looking for “top trending” content which you may want to post yourself or as part of a newsletter, we have made it easier for you to see what is the most shared content on each article where it says “XX influencers shared”. You can also explore who those influencers were that shared it.

The ultimate question I’m sure you are wanting to know the answer to … How is the influencer score worked out? There’s is a complex algorithm, but the key takeaway that you need to know is that topical influencers are the social experts on a topic within the Cronycle and Right Relevance platforms. The score provides a measure of the social capital earned by an influencer in a topic.

Start Exploring