Get predicted Engageability of messages with Intuition model
Updated
Brands get thousands of messages daily on social media channels. Such high volumes of messages make it very difficult for these brands to manage their social conversations. It’s a nightmare for the community managers of such brands to go through such an enormous number of messages and based on certain brand guidelines find relevant messages on which they need to engage on. Due to this manual scanning of messages, it’s not possible to look at every message with perfect classification. Thus, a lot of messages which required a brand to engage in getting missed diluting the customer experience.
To solve this problem, Sprinklr has developed an automation system which scans all incoming messages and classifies them into one of these two categories:
Engageable: Messages on which the brand should engage on.
Non-Engageable: Messages which does not require the brand to engage on.
The Engagement Intuition model classifies on the basis of text content and is applicable across channels as well as on both owned and earned data.
Guidelines of Engagement
These guidelines define the overall approach to social engagement for brands which is followed by the Engagement Intuition model to predict engage ability of a message.
Based on message
Based on the social profile
Based on conversation history
Based on Message
Engagement Intuition model reviews the customer motivations and the content of the post to determine if it meets the criteria for responding as given below.
Prediction Based on Customer Intention
What to Engage | |
Message Type | Example(s) |
Fans who are excited about the brand |
|
Fans who show love for the brand or its products or services |
|
Expressing Interest or intent to buy a product/service (existing or future coming) |
|
Individuals who need to be educated on brand policy, quality, or brand guidelines, etc. |
|
Customers looking to learn more about initiatives put forth by the company or company information |
|
Customers looking for help from customer service or support |
|
What Not to Engage | |
Message Type | Example(s) |
Posts, shares, retweets by Trolls, haters, conspiracy theorists, or those looking to get attention |
|
Messages meant to spam on social |
|
Prediction Based on Content of Post
What to Engage | |
Message Type | Example(s) |
Complaining or unhappy about a product/service |
|
Having queries on how to use/configure a product/service |
|
Praising a brand for its product/service experience or innovation/achievement of the brand |
|
Mentions of non-branded products/services that brand sells |
|
“I don’t like <brand> but I love their ___” |
|
“I only like <brand’s> ____” |
|
Use of abbreviations (i.e., AF, LMAO, LMFOA, WTF) with positive Sentiment |
|
Use of Mild Swearing words |
|
Negative Emojis expressing concern or issue |
|
Other non-competitor brand mentions that don’t violate direct competition guidelines |
|
Hyperbole in expressing desire or praise |
|
Customer asking for products/services that are discontinued/limited-time |
|
Customer asking for products/services that are not available at their location |
|
Posts related to customer requirements |
|
Posts concerning the difference in availability/prices of products or services |
|
General complaints about broken products or services |
|
Positive comments by customers in reaction to a shared article |
|
Customer talking about small “freebies” received by the brand |
|
What Not to Engage | |
Message Type | Example(s) |
Sharing News articles or updates about a brand |
|
Brand or Product mention where the context is generic |
|
Unsolicited ideas from customers via owned channels |
|
Suggestions from Fans regarding brand’s Marketing or Management which will not affect the fans directly. |
|
Use of abbreviations (i.e., AF, LMAO, LMFOA, WTF) with Negative Sentiment |
|
Negative emotions expressing hate or disgust |
|
If someone comments on customer post with extremely horrific statement or offensive slurs |
|
Strong swearing or sexually explicit language that is clearly written out (configurable by rule engine) |
|
Self-censored profanity (configurable by rule engine) |
|
Hangover/Drunk References (configurable by rule engine) |
|
Reference to “food porn”, “car porn”, “fashion porn”, “real-estate porn” etc. (configurable by rule engine) |
|
Reference to illegal activity like drug use, underage drinking (configurable by rule engine) |
|
Reference to brand being unhealthy, irresponsible, non-compliant etc. (configurable by rule engine) |
|
Other Competitor brand mentions (configurable by rule engine) |
|
Posts that have no merit beyond their own personal agenda or desires |
|
Posts that reference a program that hasn’t been officially rolled out, is no longer available, or isn’t part of the brand (configurable by rule engine) |
|
Questions regarding private company financial data (e.g. sales figures) (configurable by rule engine) |
|
Posts that use the word “addicted” or “fix” in context with products/services fo brand (configurable by rule engine) |
|
Posts asking for or mentioning health and dietary issues. (configurable by rule engine) |
|
Straight retweets, where customer does not add a comment to the conversation. (configurable by rule engine) |
|
Messages in non-relevant languages (configurable by rule engine) |
|
Based on the Social Profile
Classification can be enhanced by configuring profile conditions in the rule engine so that posts from only genuine profiles are marked as engageable.
What to Engage | |
Message Type | Example(s) |
Handles of genuine individuals (profiles not in exclusion, Do Not Engage, Spam or Blocked profile lists) |
|
Verified accounts by social network | NA |
Social Influencers (configurable by rule engine, using profile lists) |
|
Mild curse words and self-censored swearing in profile bio/description (configurable by rule engine) |
|
What Not to Engage | |
Message Type | Example(s) |
Parody accounts and fraudulent handles (using exclusion, Do Not Engage, Spam or Blocked profile lists) | NA |
Bio containing strong cursing, sexual references, drug references, violence or racial slurs should not be responded to* (configurable by rule engine) |
|
Commercial, non-individual or media accounts (using exclusion, Do Not Engage, Spam or Blocked profile lists) | Handles of businesses, school accounts, furry or fetishized personas, super-fan, media, industry-focused or other entities |
Brand employees on social media (using Employee profile lists) | NA |
Based on Conversation History
In order to maintain the context of the conversation, the rule engine can be configured to mark messages of relevant conversations as engageable.
Rule 1: Messages in active conversations or have open cases are classified as engageable.
Rule 2: Messages older than a specified period of time e..g 4 days are classified as non-engageable.