This report is a series of snippets from graph analysis of engagements and conversations including retweets, mentions and replies related to the Dreamforce conference (Oct 4-7) by Salesforce.
Data & Duration: The report uses over 200K tweets sampled from 25th September to 8th October. This along with Right Relevance topics and topical communities’ data form the basis for the analysis.
The phrases used for gathering tweets are: [“dreamforce”, “dreamforce16”, “dreamforce2016”, “dreamforce’16”, “df16”]
The Dreamforce analysis collateral is available in the form of:
- Tableau Online Dashboard
- Gephi Graph Visualisation of Communities
Communities & Influence
Identifying communities and determining influence of active parties that form the sources of data are critical to the Insights analysis.
Measuring influence is not deterministic. It’s a fairly subjective task with numerous different methodologies and is generally ephemeral in nature. Using graph theory, machine learning and natural language processing, RR discovers how people congregate to form communities that share common interests, within the context of an event (or topic or trend). We also determine influence within those communities, along longer and shorter timelines. At Right Relevance, we measure influence in 2 distinct ways:
‘topical influence’ or Tribes by measuring the quality of network connections within the context of a ‘topic’ and,
‘engagement influence’ or Flocks by measuring quality and quantity of engagements (RTs, mentions, replies), reach of tweets, connections etc. within the context of an event or trend.
The analysis methodology is outlined at http://184.108.40.206/insights
1. Salesforce Developers & Admins Flock
As expected, Salasforce developers and admins were out in force and strongly connected at DF16 leading. They formed a fairly tightly knit community leading to several well-defined flocks being formed along with a much larger community as seen by the single color in the graph below.
Top strongly related hashtags: #awesomeadmin, #trailhead, #dfoutpost, #wit, #devforest, #appycamper
#wit hashtag was in close proximity to the Salesforce developers community. Great to see that DF16 provided more visibility and recognition to Women-In-Technology.
2. Philanthropy Flock
@benioff was front and center leading the Philanthrophy flock as seen in Figure 3.
#dfgives, #endaids were the 2 driving hashtags around the Philanthropy flock.
3. Vala Afshar Flock
Top hashtags like #cio #cx #cmo #martech outline the executive skew of this flock.
Figure 3.3 is shows the Reach Vs Rank chart for this flock.
4. AI, Salesforce Einstein Flock
The top hashtags (#ai, #einstein, #futureofwork, #iot) & RR topics (cloud computing, data analysis, data science, iot, technology) clearly show the technology focused nature of this flock.
The Gephi graph (Figure 4.2) shows the tightly connected nature of this community in terms of engagements.
5. Customer Success Flock
There seems to be a customer success & sales related flock around @IFTTT it’s CEO @ltibbets and @GainsightHQ and it’s CEO @nrmehta. Other notable users include @6senseinc and it’s CEO @amandakahlow, @socialmktgfella, @sendgrid and Gainsight investors @salesforcevc, @bessemervp and@bdeeter.
There is intemingling with the #dreampitch event as a few VC related accounts were engaged with this flock.
The sub-graph (Figure 5.2) shows the users in this flock engaging with each other leading to them being closely connected.
6. InsideView Flock
Top hashtags include #abm (‘account based marketing’), #openlounge, #whereisyourroi, #flipmyfunnel which are related to the marketing and sales business of the company and user accounts engaged in this flock.
Figure 6.2 shows the closely connected sub-graph around this flock in the overall DF16 graph.
7. Salescloud Flock
The top Right Relevance topic is ‘social selling’, which shows the strong affinity with the area of sales as confirmed by the top hashtags.
@gabevillamizar is a top user too but this could be due to the BOT effect as outlined below and something that needs deeper analysis.
8. BOT Effect
There seems to be another flock around the topic of “social selling” that seems to be bot generated and managed. @Timothy_Hughes seems to be the primary driving account with @imoyse and potentially @gabevillamizar providing fairly good support.
All 3 accounts have a high number of followers and show a lot of engagement. This looks like a case of bot job well done.
The interesting thing to note from the sub-graph is that the self organizing nature of graph algorithms have brought these accounts to the edge of the larger DF16 graph and into a tighter knit community. This could be since they’re potentially engaging with each other more due to the automated nature.
This needs more looking at and looks like a good case study for a deeper analysis.
The series of snippets above form a small portion of the overall analysis. Please email firstname.lastname@example.org if you notice yourself in the graph and would like the information.