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 events like elections, brands, emerging technologies, issues/activism, conferences, product launches etc.
This report is a summary of graph analysis of engagements and conversations including retweets, mentions and replies of tweets from May-June 2017 on terms related to GMOs.
The report leverages tweets sampled from May 1st to June 30th 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 [“gmo”, “gmos”, “genetically modified”, “geneticallymodifiedfood”, “geneticallymodifiedfoods”, “geneticengineering”, “genetically engineered”, “geneticallyengineered”]
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 access to Tableau and the complete graph please send email to firstname.lastname@example.org.
The analysis methodology is outlined at https://info.rightrelevance.com/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.
The GMOs communities’ graphs; both all engagements which includes mentions (fig 1) and RTs-only (fig 2); show a strongly partisan split into pro-GMO (green) and anti-GMO (pink) supporters. This is similar to our graphs for the US election analysis and prior GMOs analysis in January 2017. Another obvious thing to note is the relative sizes, pro-GMO is much smaller than anti-GMO.
The retweets-only graph (fig 2) is just as stark in bringing out the partisanship. It also shows that anti-GMO is made up of several smaller communities (denoted by different colors). The pro-GMO community, though visibly much smaller in both graphs, seems more cohesive esp. in the RTs-only graph.
We’ll dive deeper into the sub-communities and the leading users driving each sub-community in the Flocks section.
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.
Looking at the trending terms, hashtags and RR topics (Fig 3), we can make out the following top themes driving conversations:
- Monsanto features prominently esp in context of Pesticides, Glyphosates, Roundup
- Organic food, boycotting GMOs based food, healthy eating.
- GMO food labeling, though a top theme, seems less intense in May-June’17. The main one being GMO labeling bill in Canada.
- GM Mustard issue in India.
The communities, users and tweets related to the top themes will be outlined and discussed in greater details below as we delve deeper.
The top tweet, by a long distance, in this timeframe is as shown below in Fig 4.
Unlike Jan’17, when 3 of the top tweets were pro-GMO, all the top tweets are overwhelmingly anti-GMO. The top 7 tweets are all anti-GMO.
Themes via Location Faceting
India GM Mustard
Selecting ‘Delhi, India‘ from the locations box makes the ‘GM mustard’ theme obvious from the associated tweets. It was the primary issue driving GMO conversations in India and part of the broader anti-GMO conversations.
Trending terms (mustard, india, farmers, crops, latest, ban), hashtags (#nogmmustard, #gmmustard) and top tweet related to the location facet confirms the above.
EU GMO vote
Selecting ‘Brussels, Belgium‘ from the locations box reveals the EU GMO Vote as the major theme in EU GMO conversations. GMOs again failed to garner enough support can be determined from the tweets and the top tweet (fig 7).
Canada GMO Labeling Bill C-291
Selecting ‘Toronto, Canada‘ from the locations box shows the focus on GMO labeling bill ‘C-291‘ in Canada. It failed to pass in the Canadian parliament can be discerned easily from the top tweet (fig 8).
Accounts via RR Topic Faceting
Using Right Relevance topics as facets (via the Insights Tableau dashboard) is a great way to pinpoint top accounts connected to a related theme within the broader context.
The top influencer accounts for ‘biotechnology’ within the context of ‘GMOs’ conversations and engagements are outlined below.
The top 5 ‘GMOs – Biotechnology’ conversation related accounts are Monsanto Company (@MonsantoCo), Kevin Folta (@kevinfolta), GMOAnswers (@GMOAnswers), Genetic Literacy (@GeneticLiteracy) and C. S. Prakash (@AgBioWorld). As expected, there is skew towards pro-GMO accounts/users.
Measuring influence is not deterministic. It’s a subjective task with numerous different methodologies and is generally relatively dynamic and ephemeral in nature. Right Relevance platform measures users/accounts influence in 2 distinct ways: topical & engagement-based.
Right Relevance algorithmically mines web content and social media at scale to determine topics and influencers and produce a measure of influence per topic termed as ‘topical influence’. Unstructured text, network connections, 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 health food, organic products, veganism, gluten free diet, vegetarian diet, nutrition and agriculture among others.
Fig 10 also provides a list of the top 10 Right Relevance ‘GMOs’ influencers along with the top 10 domains where influencers post about ‘GMOs’.
Right Relevance ‘engagement influence’ measures are calculated by applying a set of graph analysis algorithms, including PageRank and Betweenness Centrality.
The quality and quantity of engagements (RTs, mentions, replies), reach of tweets etc. are measured within the context of a subject (event, trend etc.). to measure Flock influence. The meaning of rankings within this methodology are documented at Twitter Conversation Performance Measures.
The first two lists (fig 11) 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’).
Roe (@tsunamijamani) has the highest PageRank due to extremely high engagement for the tweet in the ‘Top Tweet’ section. This makes her the top Flock influencer for ‘GMOs’ though she’s not a ‘Tribe’ influencer. PeezyPlates (@NdigoJones) has high PR as she has engagement from Roe. YouTube (@YouTube ), Monsanto Company (@MonsantoCo) and Food Evolution (@foodevomovie) round up the top 5 by the PageRank measure. Top Overall, in spite to the normalized nature, didn’t bring up many new users to the top apart from moving GMWatch (@GMWatch) to the very top.
YouTube, Donald Trump (@realDonaldTrump), Dept of Agriculture (@USDA), US FDA (@US_FDA), CDC (@CDCgov), Neil deGrasse Tyson (@neiltyson), Bill Nye (@BillNye) etc., in some cases may not have much to do with GMOs directly 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. YouTube’s ascension probably shows that the amount of video content in GMO conversations has increased massively since the last analysis in Jan’17.
Below (fig 12) are the top 30 accounts by PageRank and Top Overall measures from Jan’17 analysis for comparison.
The results above lead to other measures becoming important to measure influence as discussed below.
One of the most reliably useful and interesting measures is ‘Top Connectors’. Fig 13 shows the top 30 accounts by this measure, which is on ‘Betweenness Centrality’ algorithm.
Betweenness 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 the PageRank and Overall measures. Most of the well-known high followers count unrelated accounts like Donald Trump, YouTube, CNN etc. are absent. All the top accounts like GMWatch (@GMWatch), Kevin Folta (@kevinfolta), HealthyOrganicGreen (@H_O_G_), Rachel Parent (@RachelsNews), CaligirlBerner (@Twitlertwit), 8extremes (@8extremes), Food Evolution (@foodevomovie), Project Nature (@NOtoGMOs) seem like activists, blogs etc. and are big hubs of information dissemination.
When compared with the list (fig 14) from Jan’17, many of the accounts seem to be common with Food Evolution (@foodevomovie) being a top new entrant.
The value of this measure lies in that it bubbles up accounts with influence in terms of news and information dissemination in this subject.
The engagements or “flocking” in the context of a subject (topic, event etc.) can lead to building of temporal communities with local influence that is not obvious by the standalone influence of the individuals or without the context of the event. The subgraphs aka communities formed by applying community detection graph algorithms are termed as ‘Flocks’.
Flocks generally align well with the subgraphs aka communities noted in the graph. As seen in the all engagements graph in Fig 1, there is one large engaged community on the pro-GMO side of the strongly partisan graph with anti-GMO divided into many active smaller inter-connected communities.
Note: Flocks are named after the account with the highest PageRank in the flock.
Some interesting flocks are outlined below.
The 1st flock, tagged ‘foodevomovie’, looks highly pro-GMO as seen by trending terms like science, evolution; hashtags like #science, #biotech, #foodevolution, #factsnotfear and RR structured topics like biotechnology, biology, agribusiness, science communications, genomics etc. Terms like ‘evolution’, ‘climate change’ and vaccines
The top users for this flock (fig 16) are very similar to the ones found using RR structured topic ‘biotechnology’ as a facet.
Couple of top tweets from this flock are:
Figure 17: Top Tweets for flock ‘foodevomovie’
‘GMWatch’ is the primary anti-GMO flock with focus on Monsanto, boycotting GMOs in general, GMO labeling, pesticides mainly glyphosate and roundup. Healthy living and diet esp vegetarian/vegan and intermingled as seen by RR topics list.
The top users of this flock seem like anti-GMO activists, blogs etc.
Fig 20 is the Gephi graph snapshot of the ‘GMWatch’ flock sub-graph.
The ‘trutherbotyellow’ flock is the same as the ‘trutherbotgray‘ flock in Jan’17 analysis. It has persisted and even grown somewhat in the subsequent months. It’s a series of connected anti-GMO bot accounts with its own echo chamber as a vast majority of engagements are within members of the flock. It does not have any real penetration in the overall GMOs conversations as observed from the graphs in Figure 1 and 2. RR normalized topic view shows ‘conspiracy theories’ as the top term. Hashtags also throw up #chemtrails, #thetruthfiles, #geoengineering etc. conspiracy related terms.
The ability to isolate such accounts as a separate connected flock for marking as BOT or SPAM or FRAUD/FAKE is one of the strengths of this analysis from relevance, trust and verifiability point of views. Fig 21 visualizes this:
A few quick observations of note are:
- Easily identifiable and deeply partisan pro-GMO and anti-GMO communities with each having its own echo chamber.
- Anti-GMO is visibly much larger in size with broader reach. Based on similar prior analysis (Brexit, US Election), it can probably be said with some confidence that anti-GMO would win a popularity contest or popular vote.
- Pro-GMO community is even more cohesive than Jan’17. Probably higher organization, very homogenous with dense intracommunity engagements leading to a single clear large community.
- Anti-GMO has aligned well with organic food, healthy diet esp. vegan/vegetarian, and healthy living to get broader information outreach.
- Pro-GMO continues aligning with high visibility pro-science issues like vaccination, climate change and evolution along with food security to increase awareness.
- Anti -GMO communities continues to seem to be winning the information war on Twitter though pro-GMO has higher cohesiveness and potentially better information penetration this time around as seen by two of the top three flocks being pro-GMO.
- Both communities continue to be top heavy with a select set of users driving the conversations. This along with the echo chambers formed needs more analysis.
Please contact email@example.com for more details.