Saudi Consumer Sentiment is lagging other markets in private business, but still gathering growth at the fastest pace since January 2020. Economic sentiment surges to series-high growth amid government intervention, while sentiment in employment is the strongest in the series, indicating better growth for the private sector shortly.
As D/A’s managing partner, Paul Kelly states “Saudi’s performance is being driven by government announcements and activity from government-related entities, as one may expect. Consumer sentiment in the economy and employment is therefore extraordinarily strong, while private business is struggling. Given sentiment is a leading indicator, we would hope private business picks up in coming months as trickle-down effects shine through.”
THE KSA SILA CONSUMER SENTIMENT INDEX (CSI)
The KSA Sila CSI is growing faster than it has in all series, although still net negative on the substantial private sector business weighing down the index. Positive sentiment grew 8 percentage points in May and continues to trend upwards. With a recovery in private sector sentiment, we expect the CSI to be net positive soon.
Consumer Economy Sentiment
The Saudi Economy CSI is driving the uptick – maintaining significant growth – with an increase of 5.7 percentage points of confidence in May, continuing a trend seen since December. Sentiment has increased largely based on government spending, announcements, and buoyant consumer spending – encouraged by government communications. We are seeing a significant divergence between the public economy and the private sector – with a net negative sentiment in private.
Consumer Business Sentiment
Saudi Business CSI continues to grow positively, albeit a long way off net-positive. Growth in May was the largest since January 2020 at 4.9 percentage points. However, the Index is still net-negative at only 29.4% net positive about business growth. Why? There is a large gap emerging between the private sector and the public sector that has been evidenced since last November. The divergence is stark and one that concerns the overall growth prospects of the consumer.
Consumer Employment Sentiment
The Saudi Employment CSI is now above the pre-pandemic level. With a very large increase of 7 percentage points, the consumer sentiment is now almost at the margin of error of +95. This indicates, along with confidence in the economy, that government communications and strategies are buoying the consumer’s confidence. Employment confidence is a leading indicator of change to actual status and consumer spending. We would expect to see a private sector trickle-down in the coming months and an improvement in conditions.
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