Enriching the Text Mining Capabilities by Transforming the Text Mining Domain to Chess Game Domain to Simulate Future Scenarios

Abstract

Text mining depends on analyzing the text on different levels: words, sentences, paragraphs, articles and the whole corpus. However, following the fixed rules of analysis from the very start to the end proved to be poor in building trends and sequence analysis of respectful quality. Our point of view is that we need a more flexible approach to predict the writer's strategy; this strategy depends on 2 factors: 1) Information gained on each level. 2) Feedback information from a lower to a higher level in order to redirect the analysis assumptions to a more fruitful route. Such general stream of thinking indicates a possible resemblance with the use of Agile [16] technique in system analysis and design. We are suggesting a technique relies on the adoption of a main strategy with possibility to reassess and act based on a closer feedback loops; such feature resembles to great extent the Chess game where we have a master plan and changeable tactics that depends on the feedback information gathered on every move. The paper presents this new methodology that enriches the results of text mining by using its output as parameters for a Chess game; the new domain has very rich historical records that help researchers in building future scenarios which is too hard to be accomplished within the text mining domain itself. This issue can largely affect the decision makers and researchers in politics and sociology. The reader may guess that some of the implementation is overlapped with classical simultaneous games or Chess MinMax algorithm; which is not true[1].

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 0 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.