Enhanced Sentiment Analysis Algorithms for Multi-Weight Polarity Selection on Twitter Dataset

Sentiment analysis is based on the orientation of user attitudes and satisfaction towards services and subjects.Different methods and techniques have been introduced to analyze sentiments for obtaining high accuracy.The sentiment analysis accuracy depends mainly on supervised and unsupervised mechanisms.Supervised mechanisms are based on machine learning algorithms that achieve moderate or high accuracy but the manual annotation of data is considered a time-consuming process.In unsupervised mechanisms,a lexicon is constructed for storing polarity terms.The accuracy of analyzing data is considered moderate or low if the lexicon contains small terms.In addition,most research methodologies analyze datasets using only 3-weight polarity that can mainly affect the performance of the analysis process.Applying both methods for obtaining high accuracy and efficiency with low user intervention during the analysis process is considered a challenging process.This paper provides a comprehensive evaluation of polarity weights and mechanisms for recent sentiment analysis research.A semi-supervised framework is applied for processing data using both lexicon and machine learning algorithms.An interactive sentiment analysis algorithm is proposed for distributing multi-weight polarities on Arabic lexicons that contain high morphological and linguistic terms.An enhanced scaling algorithm is embedded in the multi-weight algorithm to assign recommended weight polarities automatically.The experimental results are conducted on two datasets to measure the over-all accuracy of proposed algorithms that achieved high results when compared to machine learning algorithms.

Research and Realization of Ten-print Data Quality Control Techniques for Imperial Scale Automated Fingerprint Identification System

As the first individualization-information processing equipment put into practical service worldwide,Automated Fingerprint Identification System(AFIS)has always been regarded as the first choice in individualization of criminal suspects or those who died in mass disasters.By integrating data within the existing regional large-scale AFIS database,many countries are constructing an ultra large state-of-the-art AFIS(or Imperial Scale AFIS)system.Therefore,it is very important to develop a series of ten-print data quality controlling process for this system of this type,which would insure a substantial matching efficiency,as the pouring data come into this imperial scale being.As the image quality of ten-print data is closely relevant to AFIS matching proficiency,a lot of police departments have allocated huge amount of human and financial resources over this issue by carrying out manual verification works for years.Unfortunately,quality control method above is always proved to be inadequate because it is an astronomical task involved,in which it has always been problematic and less affiant for potential errors.Hence,we will implement quality control in the above procedure with supplementary-acquisition effect caused by the delay of feedback instructions sent from the human verification teams.In this article,a series of fingerprint image quality supervising techniques has been put forward,which makes it possible for computer programs to supervise the ten-print image quality in real-time and more accurate manner as substitute for traditional manual verifications.Besides its prominent advantages in the human and financial expenditures,it has also been proved to obviously improve the image quality of the AFIS ten-print database,which leads up to a dramatic improvement in the AFIS-matching accuracy as well.