Right Relevance (RR) provides curated information and intelligence on ~50 thousand topics. This includes:
- Topic relationships including related topics & semantic information like synonyms.
- Topical influencers (~2.5M) with score and rank.
- Topical content and information in the form of articles, videos and conversations.
Additionally, Right Relevance provides an Insights offering that combines the above Topics and Influencers information with real time conversations to provide actionable intelligence with visualizations to enable decision making. The Insights service is applicable to emerging events like elections, conferences, product launches, breaking news developments, outbreaks like Ebola etc.
The report leverages tweets sampled from November 24th 2016 to January 20th 2017 and along with Right Relevance topics, topical communities’ and articles data form the basis for the analysis.
The phrases used for gathering tweets are: [“Accessibility”, “Disability”, “Digital Inclusion”, “a11y”, “Digital divide”, “Neurodiversity”, “Assistive Tech”, “assistive technology”, “inclusive design”, “G3ICT”, “UNCRPD”, “Dyslexia”, “Autism Dyslexic”, “Autistic”, “Spoonie”, “SPLD”, “Colour blind”, “color blindness”, “Down syndrome”, “low vision”, “visual impairment”, “visually impaired”, “Usher Syndrome”, “guide dogs”, “prosthetics”, “fibromyalgia”]
Most of the summary report is extracted from the analysis collateral in the form of:
- Tableau Online Dashboard
- Gephi Communities Graph Visual: Extracts are shown below. For the complete graph please send email to email@example.com.
The analysis methodology is outlined at http://184.108.40.206/insights
Community detection graph algorithms like Walktrap and InfoMap are used to identify communities (as sub-graphs) in our engagements graph built using Neo4j & R. Graph visualizations are done via Gephi.
In the communities’ graph (Fig 1), several communities, identified by different colors, stand out clearly, some of which are outlined in the Flocks section of the report.
Latent Dirichlet allocation (LDA) based text analysis of the tweets is used for identifying high value trending terms. These along with hashtags and Right Relevance topics form the basis for identifying top conversation themes during the analysis timeframe.
2 major events, International Day of Persons with Disabilities and the US election fallout esp. wrt Trump’s mocking of a person with disability, unfolded during this timeframe and had a broad but diffuse impact.
Outside of that, looking at the related trending terms, hashtags and RR topics (Fig 2), some top themes driving conversations were:
- Autism, asd (autism spectrum syndrome) and asperger syndrome.
- Dyslexia and special needs education. Closely related to the above and another top theme.
- Fibromyalgia and chronic pain with #spoonie hashtag trending well.
- Issues like mental health, disability rights, human rights, social justice and national health service are other related issues that were among the top themes.
- Accessible and inclusive design and technology
One discrete event that went viral was the tragic news of a young 9-yr old autistic boy who went missing and was later found dead.
The communities and conversations related to the top themes will be outlined and discussed in greater details below as we delve deeper.
Measuring influence is not deterministic. It’s a subjective task with numerous different methodologies and is generally ephemeral in nature.
At Right Relevance, influence is measured in 2 distinct ways:
‘topical or tribe influence’ by measuring the quality of network connections within the context of a ‘topic’ and,
‘engagement or flock influence’ by measuring quality and quantity of engagements (RTs, mentions, replies), reach of tweets etc. within the context of an event or trend.
Right Relevance algorithmically mines social media at scale to produce a measure of influence per topic termed as ‘topical influencers’ or Tribes. Unstructured text, network analysis, social signals along with semantic data, ML, NLP are leveraged to produce two sets of information; a set of ‘structured topics’ (~50K) with semantic information and; a connected graph of scored ranked influencers for each of these structured topics we call ‘topical influencers’ or Tribes.
The top related topics include disability, usability, ux/ui, special needs education, visual impairments among others.
Right Relevance also identified ~5K scored ranked set of accessibility influencers on Right Relevance. The top 5 are listed in Fig 5 below.
Fig 6 provides a connected graph view of the top 30 influencers for ‘Accessibility’.
We apply several methods including PageRank and Betweeness centrality to measure the quality and quantity of engagements (RTs, mentions, replies), reach of tweets, connections etc. within the context of an event or trend. This leads to a measure of Influence based on engagements, which is temporal in nature. We call the communities detected in this manner as Flocks considering the temporal contextual aka flocking nature of the behavior.
The several ways of ranking within this methodology are documented at Twitter Conversation Performance Measures.
Rank based Influence Measure
The first two lists (Fig 7) are of the top 30 accounts by Overall & PageRank measures. Overall rank is a normalized rank to reduce the skew towards users with large numbers of followers or a single tweet having a large number of engagements/RTs (often referred to as becoming ‘viral’).
@LiveAction rank is high due to the following tweet going viral.
Users like @realDonaldTrump, @RickAndThangs, @_iamextra, @Art_FeeIs, @AmazinVoices, @SocialBehaviors, @CNN, @Rosie @YouTube round off the top 12 by PageRank measure. These accounts don’t have much to do with Accessibility per se but still have a high rank due to the virality of a 1 or 2 tweets and/or high followers count. The high ranking of these accounts clearly show the susceptibility of PageRank to high followers count or high reach (RT etc.) of one tweet.
The top overall measure, due to the normalized nature, gets rid of that bias to some extent and bubbles up several accounts like @NeilMilliken, @debraruh, @nancygedge, @DisVisibility and @akwyz, who have real influence in this subject and may otherwise be tough to discover. Still several high reach/followers account are in the list leading to other measures becoming important to measure influence as discussed below.
Connectors list is based on Betweeness centrality, which is a measure of the degree to which a node forms a bridge or critical link between all other users. We use this as a measure of influence wrt value in being information and/or communication hubs.
The first thing to notice is how this list is very different compared to PageRank and Overall measures. Most of the well-known high follower count unrelated accounts are absent.
The value of this measure lies in that it bubbles up accounts with influence in terms of news and information dissemination in this subject.
Another view to understand influence is to plot reach (audience/followers) against a normalized measure we call rank (authority). This is another great way to dampen pure follower based metrics and to bring out users that hold more sway within the community itself.
We had to trim @khou and @realDonaldTrum since they were off the charts wrt both reach and rank to enable us to show the other users more clearly.
The Reach (X-axis) Vs Rank (Y-axis) graph throws up a couple of interesting things immediately:
- The high follower accounts like CNN, Fox News, NPR, Mashable, Abc News, etc. have high Reach as expected but are either below or very close to the line diving Reach from Rank. Their influence in the Accessibility space is marginal at best but when they do speak the get a lot more audience as expected.
- The “connectors” group of bloggers, advisors etc. like David Perry, Neil Milliken, Debra Ruh, Antonio Santos, Nancy, Alice Wong et as measured by betweenness centrality above, have managed to gain a lot of traction wrt Rank even with relatively lower Reach (in terms of followers) sometimes. This could be because they are early movers and/or tightly integrated in this subject’s community.
Flocks are people engaging in conversations around events esp. in context of a specific subject, which is ‘accessibility’ terms in this case. This “flocking” can lead to building of temporal communities with local influence that can lead to virality not obvious by the standalone influence of the individuals or without the context of the event.
The 1st flock, tagged ‘erabrand’, forms a large and active community with focus on autism, dyslexia, down syndrome and rights for autistic and disabled people along with chronic pain and fibromyalgia, as seen by the trending terms in Fig 11.
Related hashtags and topics list (Fig 11) confirm the focus of conversations for this community. The top users for this flock are the same users as found by betweenness centrality (connectors) & Reach Vs Rank measures. This view provides more context around the areas of their influencer and the topics of the conversations they engage in.
Figure 12 is a snapshot of the ‘erabrand’ flock sub-graph.
‘Youtube’ is the largest flock and a diffuse mix of the following primary conversations around accessibility and disability.
- US politics and news media due to the US election fallout esp. wrt Trump’s mocking of a news reporter with disability.
- UN/WHO conversations esp. due to the ‘International Day of Persons with Disabilities’ on Dec 3rd 2016, which falls in our time window (Nov 24th 2016 – Jan 20th 2017)
- A CNN tweet (Figure ), on Dec 10th 2016, going viral about a little boy with Down Syndrome being the newest face of OshKosh B’gosh’s holiday ads.
- #axschat conversations which we’ll look into deeper as part of the flock around @neilmilliken.
The above is confirmed by top tweets for this flock in Figure 13.
The set of related hashtags and RR topics along with the involvement of broader set of accounts in the flock, like @nytimes, @Youtube, @FoxNews, @NBCNews, @guardian, @mashable, @BBCWorld, @BBCNews, @WHO, @WhiteHouse, @TIME, @TechCrunch, @Microsoft, @Forbes, @wef, @UN etc. show the broad and diffuse nature (Fig 14).
This is by far the most concentrated flock wrt engagements in the graph as can be seen in the Gephi sub-graph snapshot below.
Topics of conversations, in this timeframe, seem broad and cover autism, Asperger syndrome, dyslexia, accessible technology, disability rights among others.
Trending terms along with hashtags and RR topics (Fig 16) confirm the breadth of conversations. The top users @NeilMilliken, @debraruh and @akwyz have mentioned themselves as cofounders of #axschat explaining it’s presence as a top hashtag.
The flock ‘scope’, looking at the trending terms and top users (Fig 17), seems to center around accessibility, disability and autism related conversations in the UK context geographically.
This flock is co-located with the ‘scope’ flock in the Gephi graph with overlapping communities and colors bleeding into each other as seen in Figure 20. This is because both are discussing similar topics in the same geolocation, which is the UK.
The ‘johnprsingdns’ flock is another UK based flock with main conversation focus on the disability benefits cut.
Several top tweets of this flock are about the disability cuts in UK. For e.g. Fig 19.
This flock is co-located with the ‘scope’ flock in the Gephi graph with overlapping communities and colors bleeding into each other as seen in Fig 20. This is because both are discussing similar topics in the same geolocation, which is the UK.
The ‘SamosaManiac’ flock is centered around fibromyalgia and chronic pain conversations as seen by the trending terms and hashtags (Fig 21).
Fig 22 shows the community snapshot in the Gephi graph.
The ‘IDPwD’ and ‘PWDAustralia’ flocks cover Australia geo-located communities focused on accessibility and disability related conversations. As seen from RR topics and top users, Australian political and governmental accounts form a good part of these conversations.
Figure 24 shows the snapshot of the ‘IDPwD’ & ‘PWDAustralia’ flocks in the Gephi graph.
The ‘LFLegal’ flock is centered around conversations on accessible and inclusive technology as seen by the trending terms, hashtags, RR topics and the associated top users (Fig 25).
The top users list of this flock pinpoint some of the most important players in the space of accessible and inclusive design and technology.
The set of top tweets (Fig 26) for ‘LFLegal’ flock lists the most important developments and issues related to inclusive design and technology.
Fig 27 shows the snapshot of the ‘LFLegal’ flock sub-graph in the Gephi graph.
The top two tweets in this timeframe are as show below in Fig 28.
Accessibility, disability and related terms are vibrant topics of discussion online esp. on Twitter with several well defined communities, influential activists, engaged users and critical conversations.
There are many more details that could not be included in this report. Please contact firstname.lastname@example.org for more details.