Using social media as a central element of business growth strategy has become a norm for organizations, both small and big. Social has evolved as one of the main consumer interaction channels with its immense power to capture customer sentiments and help create meaningful business insights.
The article demonstrates the steps involved in identifying sentiments out of social media data.
This applies to all industries in the B2C space in particular, as the volume of consumers in such cases can be very high. Listening to consumers on a one- to-one basis may be not be cost effective and an efficient method. This will further become cumbersome if the industry is subject to seasonality as there can be variation in consumer responses and the business may not be in a position to scale up to this change. This can lead to undesired consequences. To address this issue, machine learning techniques like classification and prediction are great options[i].
Framework
The first step of the solution is data collection. For social media monitoring, in this article we have limited our scope to Twitter. Twitter allows to use download data real- time for analysis. Some of the parameters that can be downloaded pertaining to a tweet include username, message and location among others. On Twitter, consumers use different techniques to voice their opinions. They use hashtags which are basically keywords used by consumers to collectively express their opinions. These hashtags contain words corresponding to a particular business and can be tracked. Tweets corresponding to these tweets can be tracked real-time and be locally stored in the database.
Once the data has been collected, the next step is data pre-processing. This process contains a series of steps i.e. tokenization and lemmatization using stemming algorithms. Lemmatization is a process of removing suffixes of words to ensure that there are no two words with the same meaning. This is achieved by performing tokenization initially where each and every word is split from the rest of the sentence. Apart from these, regular expressions are used to remove special characters, numbers, stop words etc. as they have no use in the analysis.
Following data pre-processing, the next step is to use machine learning algorithms to identify the anomalies. Leveraging the knowledge of SMEs, tweets can manually be classified into appropriate categories. This will help us create the training data asset for the model. Once the model classifier is trained, opinions will be classified accordingly and can be programmed to raise an alert for the same[ii]. Businesses can further study these tweets and identify location, person etc. and take measures to address these issues.
Source: https://blog.sprinklr.com/5-stats-social-media-customer-care/
As can be seen in the infographics above, social media plays a major role in understanding customer feedback and has a direct impact on business. Organizations can leverage this framework and integrate it into their day to day activities. Typically organizations have dedicated resources who do this work manually by tracking the official Twitter and other social media accounts for any anomalies. This framework can be provided to them in the form of a platform, which can generate dashboard on a real time basis. Once anomaly is detected by the classifier, the platform can be programmed to send alerts accordingly. The framework can also be adopted and tuned to serve different BU’s and SBU’s individually as and when the need occurs.
The key challenge in implementing this framework will be in terms of training the model using SMEs or people who have knowledge about the business. This is a time-consuming activity that if done incorrectly can have negative impact on accuracy of the model. Also, training the data may need to be performed on a timely basis to keep the model up to date. Once these challenges are overcome and the model in the form of platform/software is implemented, businesses can identify their customer’s problem on a real time basis and take appropriate measures to resolve it quickly. This will help build customer loyalty and increase customer retention. Also, it will help businesses design targeted marketing campaigns to address any visible patterns in anomalies. This would also help them save costs as they need not be entirely dependent on third-party market research. With more and more customers adopting social media and with the ever-increasing rate of internet penetration in the country, getting to know customers better via the framework mentioned above is the way forward.
Reference
[i] https://www.socialmediaexaminer.com/exceptional-customer-service-on-twitter
Shalak B Mendon
Senior Executive, Wipro HOLMES™
Shalak helps clients across various domains transform their IT and Infrastructure operations through automation and AI solutions. In his current role, he is involved in the pre-sales function within the Wipro HOLMES™ and Automation Ecosystem.
Chaitra Babu Rao
Student - Computer Applications, Wipro HOLMES™
Chaitra is a Pre-Sales consultant for Wipro HOLMES™ AI Automation Platform. In her current role, she works towards understanding and improving clients’ operations’ methodology by identifying automation opportunities.
Improves overall productivity by 80% by digitizing drawings via Wipro HOLMES Engineering Drawing Digitization Solution
Large universal bank achieves regulatory compliance, reduces E-KYC lifecycle by up to 50% by rolling out Wipro HOLMES&trade enterprise-KYC solution
A leading insurance company achieves 40 times improvement in detection of fraudulent claims leveraging Wipro’s Artificial Intelligence powerhouse - HOLMES
© 2021 Wipro Limited |
|
© 2021 Wipro Limited |
Pharmaceutical & Life Sciences