Student Query Trend Assessment with Semantical Annotation and Artificial Intelligent Multi-Agents

Research in era of data representation to contribute and improve key data policy involving the assessment of learning, training and English language competency. Students are required to communicate in English with high level impact using language and influence. The electronic technology works to assess students' questions positively enabling semantics and intelligence in the field concerning education and health. Assessing the importance and complexity of the statement used in a query can save the effort needed to automate the questionnaire system involving better skill testing and formalization. Parts of Speech (POS) for a sentence can be assessed for improving and enhancing the utilization in students' querying skill in writing. Computer aided systems built-up on trained agents to assess data orientation for measuring the strength of the questionnaire as being plotted to test skill of the examinees. These agent needs to be made trained and provided with the data format capable to use for intelligent assessment and strong linkage. This can be done using platform of semantic web data model; well known as Resource Description Framework (RDF). To achieve this purposed study, we represent a methodology to identify each query statement tagged per its parts of speech. Then train agents to assess data impact in calculating complexity of each query. This tagged query is further transformed into RDF to give semantics and hierarchal attachment between parts of the speech.