UAE Consumer Sentiment towards the economy improves for the sixth straight month continuing to be at a series-high. Sentiment in business grows for the ninth straight month, albeit at a slower pace, while employment is back to growth.
As D/A’s managing partner, Paul Kelly states “The rebound in the UAE economy is continuing at pace, with the sharpest increase in overall consumer sentiment improving since March this year. Similar results in business, the economy, and employment suggest the UAE is well and truly confident about the recovery. External factors seem to matter less than they did six months ago – either consumer apathy or resilience. We choose the latter, but it will be interesting to see how the traditionally slower months play out”
THE UAE SILA CONSUMER SENTIMENT INDEX (CSI)
The UAE’s Sila CSI is at a series-high 73.8 basis points (+4) – driven largely by consumer confidence in the economy and business. The rate of increase in positive sentiment is also growing at a rate not seen since March.
Consumer Economy Sentiment
The UAE Economy CSI continues to grow at pace after last month passing the previous series high in September. Optimism about the light at the end of the tunnel of the pandemic seems to be gathering pace. At +3.5 net growth in positive sentiment between May and June, we’re witnessing growth first seen in February 2021, before news broke about Indian Pandemic issues.
Small fluctuations in sentiment that we witnessed on a daily basis as news broke have now been replaced with cautious, but strong optimism in the economy and the rebound. At this stage, the rate of growth doesn’t indicate that major global news would have a negative impact on consumer attitudes around the economy.
Consumer Business Sentiment
The UAE Business CSI has passed the sentiment of pre-pandemic levels. This means consumers are more positive towards the overall economy than any time since January 1, 2020. The rate of increase gathers pace as well, indicating that external events are not weighing on the economy as they did previously.
Consumer Employment Sentiment
The UAE Employment CSI is showing a considerable pace of recovery, and although not at full-levels seen in January and Feb February 2020, there is increasing confidence in consumer’s employment with a net positive score of 82, growing at a similar rate to other measurements in June of +3 points of positivity. As consumers become more confident in their employment, this has trickle-down effects across the economy.
About the D/A Sila Consumer Sentiment Index:
The Sila Consumer Sentiment Index (Sila CSI) is an index of over 45 million data points on social media that measures the public sentiment about the economy, business and employment in Saudi and the UAE. It excludes news, and only focuses on conversations about those particular topics. The language used is then analysed using natural language processing and AI to determine sentiment in Arabic dialects. Index scores are out of 100 (a score of 100 means 100% positive, a score of 59.5 would mean 59.5% positive, 40.5% negative).
About D/A and Sila:
D/A has built out the region’s only sentiment platform that natively works in Arabic dialect (different Khaleej dialects in addition to broader region), Sila, and within it has a sentiment index that pools together the positive and negative discussion on social media about key items of concern to consumers. We exclude news sharing from this analysis and instead look to opinion. Put simply, we use a proprietary Natural Language Processing (NLP) model to understand what consumers are feeling towards a topic, at scale. The basis of the data is a continuous analysis of around 45mn tweets over the last 17 months (excluding news articles) from the UAE and KSA that allows us to better understand consumers’ feelings, in real-time, in their language.
The sentiment model is based on the Natural Language Process – NLP techniques (MLM) and BERT-Base Multilingual Cased model for the Arabic language and is trained using a custom implementation of TensorFlow. The model involves a 3-way classification (positive, neutral, and negative). For the training and testing phases, we used ArapTweet, (a dataset of tweets from 11 Arab regions from 16 different countries, for a total of 45,000 tweets and news). and the data were divided into 3 phases: train (70%), Dev (15%), and Test (15%). The input parameters are the tweet (text), the number of words, and the weight of the business lexicon corpus. The model was trained with +31,000 tweets with 4 layers and 56 hidden units and 32 adjustment parameters. On Train set, the fine-tuned model obtains 86.09% on accuracy and 87.46% on F1 score. On the Test set, we acquired 88.19% acc and 86.51% F1 score. The testing and tuning process of the model is carried out every 2 months in order to improve the corpus and adjust the precision of the model. For explanation: 86% of the F1 score means that there is no evidence of assigning a sentiment, (this can happen when the text is very short or there is no congruence in the text or a mixture of languages), for our model, after excluding these cases, the precision ranges between 92.1% and 94.67% of successful cases, that is, the error ranges between 5.33% and 7.90% Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then runs the entire masked sentence through the model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the sentence.