How Real Time Analysis On Social Media Works
- Sentiment analysis may use word bank annotated for their arousal and their valence, i.e., whether they are positive or negative.
- If a piece of content has more positive keywords than negative keyword, it’s positive content; if it has more negative keywords than positive keywords, it’s negative content.
- Here is a process flow for opinion analysis that collects data from different sources such as Twitter, Facebook, ecommerce sites.
- On basis of some pre-determined keyword such as “important”, “experienced”, “excellent” etc we have to filter data.
- Generate sentiment of each message coming through various sources.
- Have a Storage mechanism for storing the processed data.
Understand Consumer’s Opinion on Your product
- On the basis of the collected data we generate the below chart which shows that Ally receives the highest share of positive response as they have superior competitive advantage like higher interest rate or better risk coverage products.
- Since banks rely heavily on their customer’s trust, they need to be aware of the overall conversation about them as well as product-related discussions. Deeper analysis of product-related discussions gives banks detailed insights into potential issues.
- Twitter is becoming an increasingly popular micro-blogging platform used for financial forecasting and guiding stock market.
- Over the past few years Twitter has moved the stock market with its real-time tweets.
- Hundreds of financial news publications feed twitter with real-time views, analysis & breaking news provided by crowd that is exposed by Twitter API making it a “ONE STOP SHOP” and for FREE.
- Of course this data could be curated and used by organizations for best possible “Data to decision” approach.
Real Time Stream Processing Use Cases
Stream or real-time processing found its first uses in the finance industry, as stock exchanges moved from floor-based trading to electronic trading. Today, it makes sense in almost every industry – anywhere where you generate stream data through human activities, machine data or sensors data. Assuming it takes off, the Internet of Things will increase volume, variety and velocity of data, leading to a dramatic increase in the applications for stream processing technologies. Some use cases where stream processing can solve business problems include:
- Network monitoring
- Intelligence and surveillance
- Risk management
- E-commerce
- Fraud detection
- Smart order routing
- Transaction cost analysis
- Pricing and analytics
- Market data management
- Algorithmic trading
- Data warehouse augmentation