Context Analytics (CA) is the leader in processing and structuring textual data for sentiment...
Exploring the Outback: Investigating Social Media Sentiment on Australian Securities
Context Analytics (CA) is proud to announce an expansion in social sentiment global security coverage to include Australian securities (ASX). Similar to other foreign asset classes CA covers, the ASX dataset will retrieve textual data from Twitter messages and generate sentiment scores using our proprietary Natural Language Processing (NLP) technology. These sentiment scores are actionable factors that reflect both the tone and volume of conversations at the security level. One of CA’s flagship products, the S-Factor feed, features the S-Score—a metric that quantifies the positivity or negativity of sentiment for each security.
The ASX dataset tracks over 800 securities with roughly 125 securities generating a daily signal. The S-Score, one of many factors, is a Z-Score that detects sentiment from Twitter. A S-Score greater than 2 indicates that the conversation over the last 24 hours is 2 standard deviations more positive than the previous 20 days, suggesting a bullish outlook for the stock price. Conversely, a more negative S-Score reflects negative sentiment and a bearish outlook.
To demonstrate the relationship between S-Score and future price returns, we grouped securities into daily quintiles and plot the cumulative price return. Five minutes before market close, at 3:55pm AET, we grab all securities with an S-Score published. These securities are bucketed into daily quintiles based on the value of their S-Score. Each day the highest 20% of S-Scores are grouped in quintile 5, the next highest 20% in quintile 4, and so on until the bottom 20% of S-Score are in quintile 1. We then calculate the Close-to-Close return of each individual stock, equally average the return by quintile and day to generate a portfolio of cumulative returns by quintile. Below is the plot of the quintiles’ cumulative returns sine 2021 on Twitter sentiment data.
Portfolio |
Cumulative Return |
Annualized Return |
Volatility |
Sharpe |
Sortino |
Avg. Score |
Avg. Count |
Quintile 1 |
35.81% |
9.81% |
21.52% |
0.46 |
0.78 |
-1.430 |
26 |
Quintile 2 |
106.77% |
20.03% |
21.12% |
0.95 |
1.64 |
-0.234 |
27 |
Quintile 3 |
133.76% |
22.76% |
19.78% |
1.15 |
1.91 |
0.071 |
24 |
Quintile 4 |
111.66% |
20.71% |
21.66% |
0.96 |
1.66 |
0.929 |
25 |
Quintile 5 |
324.72% |
38.05% |
22.85% |
1.67 |
2.98 |
3.248 |
26 |
The graph above shows how S-Score is a predictive metric in global markets. As the S-Score increases and reaches extreme values, indicating more positive sentiment, the security’s price is more likely to outperform the market than their peers with lower sentiment scores. Quintile 5, containing the most positive S-Scores, has an annualized return of 38% over the 4+ year back test range. One the other side, Quintile 1 containing the most negative sentiment scores, has an annualized return of 9.8% and the lowest Sharpe and Sortino ratios. These securities underperform the market average.
This blog demonstrates that sentiment data from Context Analytics and Twitter can be effectively leveraged for global trading strategies. Context Analytics’ S-Factor feed is a long-standing product that can be applied to a variety of asset classes, including Australian securities. For more information on our global coverage, please visit www.contextanalytics-ai.com .