Prior to the mid 2000’s if a customer wanted to provide feedback on a company’s service or product they would send an email, make a phone call or, gasp, write a letter to the company’s customer service department. This often required going through multiple levels of the company’s customer service hierarchy to ensure the situations was addressed. This was a one-to-one process, between the customer and the company and rarely made it beyond the four walls.
Today, social media has significantly changed the power structure of customer service in favor of the consumer. When a customer wants to share praise, ore more than likely air a complaint, they often take their opinions directly to the public through social media. When multiple customers experience similar product or service issues and share their experiences through social media the resulting negative comments can quickly become a major crisis for a company. Visa Versa, positive comments, especially by a celebrity with many followers, can send demand soaring causing other kinds of business problems. In today’s digital world, mining, analyzing and effectively responding to social media data has become a necessity for survival.
The effects of social media on business has led to an emerging practice of measuring the emotions behind social media mentions known as ‘Social Sentiment.’ Social sentiment measures the tone of the message and assigns a value or score to it based on factors such as: is the comment very positive, positive, neutral, negative or very negative? Without sentiment, data can be misleading. Just because you receive a high volume of mentions following the launch of a new product or service does not necessarily mean the new product or service has been well-received.
For any size company the process of manually sorting through large volumes of social media data to determine sentiment can be a significant time commitment. Through the use of artificial intelligence (AI) capabilities like Natural Language Processing (NLP) and Machine Learning (ML), it is now feasible to capture and mine social media data to determine social sentiment and then extend this information to calculate the probable impact on demand to help supply chain teams more accurately plan their operations.
Today’s AI solutions have the ability to correctly categorize nearly 75% of social media sentiment. As these solutions work through more data they are able to learn the difference between humor, sarcasm, irony and so on to improve their success.
Companies are starting to incorporate social sentiment into their demand sensing efforts. Sentiment scores are used along with statistical forecasts and market data like Point of Sale (POS), syndicated data, and weather data to create short term forecasts and enable an immediate response to changes in demand. Social media sentiment can also be used to uncover and evaluate potential sources of risk such as competitive new product introductions, supplier challenges or shifts in consumer tastes.
New product introductions often have limited demand histories to base future projections and can display both erratic and localized demand patterns. Social media sentiment can be used as an input to the development and launch of new products. When introducing new products, machine learning clustering techniques can be used to identify existing groups of look-alike products. A new product can be associated with an existing product cluster based on product attributes and assigned the starting sentiment score of the associated product cluster. These starting sentiment scores can help determine when and where a new product should be launched and the likely base demand and launch curve profile.
For many companies, creating accurate demand forecasts continues to be challenging due to rapid changes in customer tastes and the resulting constant stream of new product introductions. Small improvements in forecast accuracy can drive large top and bottom line financial improvements. Although the use of social media to improve supply chain planning is still very new, the potential impact to consumer focused companies could be significant. Supply chain leaders need to determine the effects of social media on the demand for their products and services and take steps to use social sentiment to improve supply chain planning capabilities.