@article{scholars13942,
           title = {A new text-based w-distance metric to find the perfect match between words},
            note = {cited By 1},
          volume = {38},
          number = {3},
             doi = {10.3233/JIFS-179552},
         journal = {Journal of Intelligent and Fuzzy Systems},
       publisher = {IOS Press},
           pages = {2661--2672},
            year = {2020},
            issn = {10641246},
          author = {Ali, M. and Jung, L. T. and Hosam, O. and Wagan, A. A. and Shah, R. A. and Khayyat, M.},
        abstract = {The k-NN algorithm is an instance-based learning algorithm which is widely used in the data mining applications. The core engine of the k-NN algorithm is the distance/similarity function. The performance of the k-NN algorithm varies with the selection of distance function. The traditional distance/similarity functions in k-NN do not perfectly handle the mix-mode words such as when one string has multiple substrings/words. For example, a two-word string of 'Employee Name', a one-word string of 'Name' or more than one word such as, 'Name of Employee'. This ambiguity is faced by different distance/similarity functions causing difficulties in finding the perfect match of words. To improve the perfect-match calculation functionality in the traditional k-NN algorithm, a new similarity distance metric is developed and named as word-distance (w-distance). The perfect match will help us to identify the exact required value. The proposed w-distance is a hybrid of distance and similarity in nature because it is to handle dissimilarity and similarity features of strings at the same time. The simulation results showed that w-distance has a better impact on the performance of the k-NN algorithm as compared to the Euclidean distance and the cosine similarity. {\^A}{\copyright} 2020-IOS Press and the authors. All rights reserved.},
        keywords = {Data mining; Genetic algorithms; Nearest neighbor search; Pattern recognition; Personnel, Cosine similarity; Data mining applications; distance/similarity metric; Euclidean distance; Instance based learning; k-NN algorithm; Similarity distance; text match, Text mining},
             url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85081537860&doi=10.3233\%2fJIFS-179552&partnerID=40&md5=2f8ba723a873404c83134a9f0365fe1b}
}