The Importance Of Textual Technology

907 Words4 Pages
Mihalceaet. al.‟s work was able to break 70% classification accuracy by using a bag-of-words model, and 10-fold cross-validation with Naive Bayes and SVM (support vector machine).Cardieet. al. Using a combination of LIWC, bigram and unigram features, they were capable to achieve 89.8% classification accuracy using 5- fold cross validation with linear SVM on written textual data [5] . Another study by (Ben Verhoeven &WalterDaelemans, in 2014) designed to serve multiple purposes: disclosure of age, gender, authorship, personality, feelings, deception, subject and gender. Another major feature is the planned annual expansion with new students each year. The corpus currently has about 305,000 codes distributed on 749 documents. The average…show more content…
The spam detection has different domains including Web (Castillo et al., 2006), Email (Chirita, Diederich, &Nejdl, 2005), and SMS (Karami& Zhou, 2014a, 2014b). The problem of opinion spam was raised by investigating supervised learning techniques to detect fake reviews (Jindal & Liu, 2008). Lim et al. (2010) tracked the Spam behavior, and found certain behaviors such as targeting specific products or product groups to maximize impact (Lim, Nguyen, Jindal, Liu, &Lauw, 2010). Using machine learning techniques is one of the popular approaches in online review spam detection. Some examples are employing standard word and part-of-speech (POS) n-gram features for supervised learning (Ott et al., 2011), using a graph-based method to find fake store reviewers (Wang, Xie, Liu, & Yu, 2011), and using frequent pattern mining to find groups of reviewers who often write reviews together (Mukherjee, Liu, Wang, Glance, & Jindal, 2011; Mukherjee, Liu, & Glance, 2012) [8] . The Most Effective Technique in the literature comes by (AmirKaram& Bin Zhou in 2015) which incorporated an additional 224 features, LIWC+, based on based on the different sets of the raw features collected from LIWC. For example, derive relative polarity by examining the difference between the degrees of positive and negative emotions. Call this extension of LIWC
Open Document