Marketing Budgets & Social Media
Anticipation is high for the payback of social media marketing investments. The verdict is out for capturing any quantifiable results. A recent CMO poll completed cosponsored by Duke Business School and Deloitte Touche indicated the following:
- 86% of the executives surveyed have social media marketing in the budget
- Average percentage of marketing budget spent on social marketing – 13%
- Increased spending has only resulted in moderate perceived value (3.4 on a 7-point scale)
- Percentage having a good idea of the qualitative and not the quantitative impact – 37.6%
- Percentage not having shown any impact to date – 32.4%
Isolating Social Media’s Value
With only 30% being able to show demonstrated quantifiable value, it is a bit surprising that a five-year growth projection of social media becoming 21.5% of the marketing budget. These views are held with a social media ecosystem that is in a constant state of flux. Simplifying the challenge, social media is an ecosystem where there are 3 broad forces in play: two which must be sensed and adapted to for survival and one with mindful choices it is possible to influence. First, at any given moment, it is impossible to anticipate what is happening on the internet in general or specifically with social media. Second, we are victims of “original sin,” what has been posted in the past and what followers have grown to expect. But it possible to influence the third force by what is actually introduced and how it is shared. How it is constructed and shared influences how it will be received.
“It’s in the way that you use it.” (thank you Eric Clapton).
Value Tracking with Lagging Indicators
To achieve a quantifiable benefit, social media must drive to outcomes with business value. Driving users, clients, or customers through the marketing funnel. For eCommerce, the outcome is getting a loaded shopping cart and committing to buy. For concerns offering services and/or building a brand image, it is attracting eyeballs “from the wild,’ and migrating from reach/impressions to followers. Followers that value the trust relationship and are willing to repurpose posts and keep the migration process going. The most frequent approach tracks progress by using standard analytics based on lagging indicators. The intent to determine what was an effective post, but resorts instead, to just comparing summary statistics for a given time period. This can show that the process is directionally correct but:
- There is no detailed data on how the present position was attained.
- No clear direction on how to maintain or change course for the future.
Sentiment Analysis Influences Desired Outcomes
So, for a particular campaign or post, what is the “right” post content, word choice, and composition for influencing the desired outcome. This can be accomplished using a two-pronged approach. First, is the evaluate the overall context and sentiment of each sentence. Then the contribution of each word of the sentence needs to be determined. The goal is to determine the predilection, sentiment, required to influence the desired outcome. Word level lexicons exist indicating the sentiment that a word can generate. Due to the “beauty” of the English language, some words can generate multiple sentiments. The bottom line, the words matter.
Sentiment Tools Focus Intent
The process for addressing these challenges starts with screening the post using AI natural language tools. This identifies the sentence level sentiment (degrees of positive or negative). Select tools also define the words from within the sentence with their respective sentiment and how they contribute to the overall sentence sentiment. After the screen, there may be an opportunity to replace negative words or replace less positive words with appropriate synonyms. The sentiment of synonyms can be assessed through the use of open-source lexicons (nrc, bin, afinn) which can be customized for specific business use. After changes to the post, resubmission to the AI tool will assess the impact of the changes. When satisfied the reviewed text can be posted.
Analytics are then used to track the posts’ performance. Post analysis establishes a valence score by combining the values of all the sentiments of the words used, and word usage at the post level. This approach is not intended to be prescriptive, like taking a pill and always getting the desired outcome. The creative resources building the content must consider followers, trending topics, and branding guiding principles in developing posts and campaigns.
Focusing Sentiments for Value
This approach and set of tools assist in building a set of leading indicators to be proactive in the social media ecosystem. It is important to remember, that there are two forces that we cannot control and need to understand the associated indicators to monitor so that it is possible to adapt as the ecosystem changes. It is the variability of all three forces that should keep us grounded by George E. P. Box’s counsel, “All models are wrong, some are useful.” Assessing and maintaining usability is a constant task given the nature of the social media ecosystem.
Value Guiding Correlating & Searching for Causation
Before the days of satellites, there was celestial navigation, where three heavenly bodies were used to determine a fix or location on the ocean as an input on any required course corrections. At Yalo, we use a combination of pre-post screening, analytics, and sentiment word analysis to asses our ability to influence funnel efficiency. These three techniques determine where we are in the social media ecosystem and how we plot our course going forward.