S-Factor Social Sentiment Data for Futures

Context Analytics, formerly known as Social Market Analytics, has expanded its depth of data to include all textual data. We source, clean, structure, and analyze textual data for investable insights and business intelligence.

The S-Factor data feed aggregates the Twitter conversation over the last 24 hours and compares it to a twenty-day baseline. 19 metrics are published every minute. CA's patented sentiment engine scans the full Twitter firehose for relevant Tweets. Patented natural language processing calculates sentiment on each Tweet which is then aggregated. Snapshots can be requested at time periods (1m, 15m, Hourly, Daily, etc.).

The sample dataset includes 15-minute updates from the past 3 years of out of sample data for US equities derived from Twitter. The 19 available metrics include:

-S-Score: The normalized representation of a security’s sentiment time series over a lock back period
-S-Volume: The Volume of indicative tweets contributing to a security’s S-Score at an observation time
-S-Dispersion: A measure of the diversity of Twitter sources contributing to a security’s S-Score
-S-Volatility: A measure of the variability of a stock’s sentiment time series over a look back period
-SV-Score: The normalized representation of a stock's indicative Tweet volume time series over a look back period

Dataset Overview:
-Coverage: 106 futures
-Geographic Coverage: United States
-Industry Coverage: All
-History: 2012
-Data Source: Twitter

Visit our website (https://www.socialmarketanalytics.com) for research and blogs of the returns:

https://www.contextanalytics-ai.com/2021/01/04/sma-futures-data-sanities/

搜集汇总

背景与挑战

背景概述

该数据集基于Twitter文本数据，通过专利情感分析引擎计算得出19个度量指标，如S-Score和S-Volume，用于监测期货市场的社交媒体情感。它覆盖106种美国期货，历史数据从2012年开始，提供15分钟更新频率。