Abstract
Social Media has been recognised as a supportive tool in Education,
encouraging student collaboration, class interactions and
communication between instructors and students. Active informal
interactions and feedback between instructors and students
outside class is one of the main reasons behind Social Media pedagogy.
Despite the prevalence of traditional email methods of providing
feedback to students, many studies show that they do not
check their emails as frequent as they check their Social Media accounts.
Social Media has also proved to create substantial benefits in
Marketing, creating a platform for brand awareness and customers
interaction. Advertising on Social Media is one of the fastest ways
to reach a large group of targeted customers. In the present day,
there are large volumes of advertisement campaigns designed for,
and running on Social Media, yielding significant conversation rates
for businesses. Advances in Artificial Intelligence (AI) have offered
techniques such as Big Data Analysis using Machine Learning to tailor
educational content and advertisements based on student’s academic
performance and consumer’s browsing patterns. With many
innovative methods of using Social Media, this creates new opportunities
in the use of AI. This work proposes the automatic synthesis
of tweets within the context of Marketing and Education, by employing
techniques in Natural Language Generation (NLG) based on Formal
Language Theory. We present an algorithm based on Contextfree
Grammars; a formal technique for describing or generating languages.
We also present two tools, the Tweet Synthesiser for automatic
academic notifications/feedback and Sell-Bot for Social Media
Advertising. A survey of 116 student participants at a South African
university on the Tweet Synthesiser showed that the majority of the
students will love to get such notifications on Social Media, rather
than check their emails; and that Lecturers also find this initiative to
be a forward thinking one. An evaluation on Sell-Bot showed that
42% of the participants did not know whether the AI or the human
composed an advert. These tools are expected to relieve humans of
their efforts of creating and sending out unique content.