Message Sequence Statistical Analysis
The invention subject is the technology for identifying statistical links in the sequence of news items, adverts, or other messages. Incoming messages are classified according to several attributes. Selective reclassification is used to account for different trait assessment interpretations. The messages converted into code form an estimator matrix. To detect a pattern in a message sequence on a timescale, it is necessary to compare matrix fragments which follow either before or after messages with the same assessment value according to one or more traits. The correlation dependence with the same data filter on the superimposed time segments is assessed. If the correlation dependence for two or more matrix fragments is high, the data filter becomes narrower. Data on settings and search results are stored in the database as a pattern. The examples discovered are assessed by a person for significance. A new or repeated pattern search starts with settings combining two or more known patterns with similar message codes. The patterns with high significance assessment are more often used to create combined search settings. The data filter is additionally extended using random values. Figuratively speaking, the pattern search criteria evolve by crossing, mutation, and selection. The analysis predictive power is expressed in the assessment of probability with which the new or probable message fits into the previously identified pattern. The past message sequence examples show what typically happens under similar circumstances.
There is no intention to replace a human but to expand cognitive abilities using additional memory and collective experience analysis.
Applications (horizon 2 to 10 years):
1. News Analysis. Detecting cause-effect relations.
2. Showing conflicts by paradox patterns. The patterns indentify groups of people with different value judgments about similar messages.
3. Inferring relationships between user data and the targeted advertising content.
4. Inferring loyalty conditions. For example, the price change pattern shows which users are provided with special conditions.
5. Message source assessment. Identifying patterns used for marketing, sophistry, NLP, pick-up, prank, and others.
Why is a technical analysis of news necessary?
Governance is a technology which is based on experience. If public opinion is manipulated in a repeatable way, the algorithm will indicate anomaly and similarity. Suspicion is still not an accusation. However, when patterns are discovered, manipulators' reputation is destroyed.
How does technical analysis work?
First, I collect data for the last 20 years, and Excel is my tool to achieve this objective. Based on the materials covering the first 20 years of the new millennium, it'll be possible to issue a review in "Namedni" style by Leonid Parfenov.
I rate noticeable events from the news feed according to eight criteria which use 124 signs. Therefore, I get the matrix with nine dimensions for technical analysis. Using data obtained, I construct data volume variance graphs and derived function variance graphs with respect to time. It's possible to calculate graph correlations average values and detect local anomalies. To analyze it in detail, the selected message is superimposed on the timeline with similar events, and this is done in each category. Graphs correlation between the merged time intervals around similar events is assessed. The connections detected are enhanced by excluding the parameters weakening the connection from the graphs. We can easily explain many dependencies, but unexplained dependencies can also be found. If the news suspiciously fits into the previously identified sequence patterns, we get predictive power based on mathematics. If the comparison turned out to be interesting, it'll attract attention measured in the number of views. People's attention is the feedback for artificial intelligence which will automatically start searching for heuristic combinations.
At the first stage, I elaborate classification criteria and analysis algorithms. Later on the Internet platform Analytica.Today will become a rating agency for the news. In some years an algorithm for assessing the conversation partner's ingenuity, sincerity, and interest can become one of the commercial products. It's not a tool for submission but a tool for detecting dishonesty.
The project development speed and the data processing scale depend on resources. The first stage will cost 100,000 Euros, and by the time artificial intelligence is launched, I would like to attract more than a million. That's why I am looking for support from wealthy people in the first place. In case the government donates a grant, I will accept it and boast about it.
I'm scared of a short planning time frame. With a short planning time frame, deception and violence provide an advantage. The more deception is practiced, the shorter the planning time frame is. This is a regenerative feedback.
Contradictions may be eliminated by suppressing defiant people or by revealing causes leading to conflict. To make decisions, the authorities need a reason in the first place, and then they need excuses. Crowd opinion is based on little news which many people have become aware of. Juggling with facts happens regularly. However, artificial actions leave traces.
The Analytica.Today project is important for conspiracists and anti-conspiracists. If the interrelation between conflicts and natural phenomena is discovered, it means someone has such a blackmail instrument. This is interesting, and people's attention is a liquid commodity nowadays. It's only a matter of time to find interesting connections if you have a large amount of data.
Artificial intelligence for Homo Sapiens :)