Saudi consumer sentiment in June surpassed pre-pandemic levels for the first time, indicating a broader rebound that has in recent months been dominated by the public sector. The rate of growth in economic sentiment has slowed slightly, while employment sentiment is now at the margin of error. The private sector is still weighing down the economy.
As D/A’s managing partner, Paul Kelly states “As we saw in May’s results, the economy is still being driven in terms of consumer sentiment, by the public sector. Growth is occurring sharply in economic positivity, but most of all is employment which is not only at a series high but approaching the saturation of the margin of error for the index. At full confidence, we might expect some inflationary issues in the future.”
THE KSA SILA CONSUMER SENTIMENT INDEX (CSI)
The KSA Sila CSI for the overall sentiment is now almost at net positive. It has just passed pre-pandemic levels, indicating that consumers are generally feeling as confident as they were in January 2020. The rate of growth at +2.3 basis points is the slowest since December 2020 and should be watched. This appears to be a largely lagging private sector.
Consumer Economy Sentiment
Economic sentiment is still growing with a score of +85 in consumer confidence for June. As the rate of Saudi government
announcements slowed down, so too has the sentiment in the economy, albeit still growing. At +2.7 it is the slowest growth in
overall sentiment since a decline in December 2020. It is noteworthy that all economic confidence is coming from government
sources and announcements, rather than a mix of sectors.
Consumer Business Sentiment
Saudi Business CSI continues to grow positively, but at a slower pace than other indicators and still net-negative (below 50 points) at 31.2. The rate of growth of +1.4 points is the slowest since the December 2020 decline, and it appears the trickle-down effect of government reforms are not being felt sharply in the private sector as of yet. Net growth in sentiment is a positive result, but is still some way off the January 2020 levels.
Consumer Employment Sentiment
The Saudi Employment CSI is now almost at the margin of error of the index, meaning almost complete positivity towards employment and a very stable June. The rate of growth in June was slower than May, which may be seasonally expected. With such strong confidence, at +94, we may reasonably expect wage growth may weigh further in the economy as the labour market becomes more competitive for employers seeking talent – albeit with a high unemployment level this may be tempered for some time.
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.