Aston University PhD Student Develops Model to Enhance Businesses’ Understanding of Customer Sentiment Online
An Aston University PhD student has come up with a new way to understand people’s feelings through their text and emoji use on social media.
Qianwen Ariel Xu, who studies sentiment analysis models, made a special computer programme that can accurately establish emotions in a way that makes it easier for businesses to understand customer sentiment and keep up with fast-changing digital trends.
A sentiment analysis model is an algorithm that reads text to determine whether the sentiment is positive, negative or neutral. It does this by looking at the words and emojis people use. These models study what customers think about products, analyse feedback and establish potential social media trends.
The model combines multi-view learning and explainable artificial intelligence (XAI) that enhances the accuracy and interpretability of sentiment analysis for high-stakes decision-making. It incorporates emojis with text to offer deeper insights into sentiment, filling a gap in sentiment analysis by simulating real emoji usage, helping businesses to make better decisions based on what people are saying online.
Qianwen Ariel Xu said:
“This new model needs very little data preparation, making it quick and precise when analysing big data sets.
“This is great for businesses trying to keep up with fast-changing digital trends.
“Understanding market trends and what customers want, especially in real-time, is more important than ever with today’s fast-paced business changes.
“I am excited to see how this work can be applied to real-world challenges and look forward to further advancing the field of sentiment analysis.”
Professor Victor Chang, professor of business analytics at Aston University, said:
“Ariel’s research exemplifies the cutting-edge, impactful work being undertaken by our PhD students at Aston University.
“The research aligns closely with Aston University’s commitment to delivering high-quality, applicable research as part of its Research Excellence Framework (REF) 2029 and Aston 2030 strategy.
“Ariel’s Google Scholar citations have now surpassed 1,000 and has published extensively in reputable journals. She has been regarded as a young rising star by her peers.
“Her innovative approach to sentiment analysis has the potential to transform decision-making across sectors, from marketing and customer service to public policy.
“We’ve discussed this research for two years and we are immensely proud of her achievements.”