(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 10, No. 12, 2019 27 | Page www.ijacsa.thesai.org Words Segmentation-based Scheme for Implicit Aspect Identification for Sentiments Analysis in English Text Dhani Bux Talpur 1 School of Information and Communication Engineering Guilin University of Electronic Technology Guilin, China Guimin Huang 2,* Guangxi Key Laboratory of Trusted Software School of Computer Science and Information Security Guilin University of Electronic Technology, Guilin, China Abstract—Implicit and Explicit aspects extraction is the amassed research area of natural language processing (NLP) and opinion mining. This method has become the essential part of a large collection of applications which includes e-commerce, social media, and marketing. These application aid customers to buy online products and collect feedbacks based on product and aspects. As these feedbacks are qualitative feedback (comments) that help to enhance the product quality and delivery service. Whereas, the main problem is to analyze the qualitative feedback based on comments, while performing these analysis manually need a lot of effort and time. In this research paper, we developed and suggest an automatic solution for extracting implicit aspects and comments analyzing. The problem of implicit aspect extraction and sentiments analysis is solved by splitting the sentence through defined boundaries and extracting each sentence into a form of isolated list. Moreover, these isolated list elements are also known as complete sentence. As sentences are further separated into words, these words are filtered to remove anonymous words in which words are saved in words list for the aspects matching; this technique is used to measure polarity and sentiments analysis. We evaluate the solution by using the dataset of online comments. Keywords—Implicit aspect; explicit aspects; polarity; sentiments analysis I. INTRODUCTION With the advancements in the field of technology more and more peoples are in touch with online shopping websites and these numbers are increasing day by day. This innovative move transfer street shopping into online shopping. The most popular trending websites includes Taobao, JD, Alibaba and Amazon etc. These e-commerce websites generally provide an easy and accessible platform for customers, where consumers can share the experience with feedback regarding products. With the help of these feedbacks it is easy to extract opinions and aspects of entities from various online comments of consumers as these reviews can help to provide opinion which can further use for prediction. The feedback help consumers know about popular trends and aspects of these products to buy. Recently, different approaches are introduced on this field as few models were also proposed to process specific task. These specific tasks are the basic part of the NLP application is words segmentation, the procedure of separating and dividing the sentence into a single token of words is called Word Tokenization [1]. In Natural Language Processing (NLP) the term tokenization or word segmentation is thought as the most important task [2]. Mostly each application of NLP needs at a certain level the process of breaking its text into distinct tokens for processing. The tokenization and extraction method is done by identifying word borders in languages like English where punctuation marks or white spaces are used to isolate words [3]. Many sentiment analysis tools and applications have been developed to mine the opinions in user-generated content on the Web. However, the performances are very poor due to the complexity of natural language [4,5,6]. In essence, sentiment analysis is still a problem of natural language processing (NLP), which deals with the natural language documents, which are also called unstructured data [7]. Prior researches show that sentiment analysis is more difficult than the traditional topic-based text classification [8]. Although various methods have been projected to conduct sentiment analysis, it is still difficult to deal with some linguistic phenomena, such as negation and mix-opinion text. This indicates to low accuracy of sentiment classification [9,10]. Besides, it is insufficient to only determine the polarity of the opinions, since an opinion without a target is of limited use. The task of extracting the opinions and their targets simultaneously is also called aspect-level sentiment analysis in the research literature and is more difficult to achieve [11]. Furthermore, in order to achieve the finest information that is required for such analysis, the different aspects and features of a product or service must be identified in the comments section. There are different examples of such features include size, price, service and parts of product aspect which are mentioned in this text. Some of the examples are illustrated below. “The mobile size is very large but picture quality is awesome and price is cheap”. In this sentence „size‟,‟price‟ and „quality‟ are all aspects on which sentiments is expressed. In the proposed work, it is consider how to extract the implicit aspects and sentiments analysis on an aspect level. The recent research has concluded that there was no parallel development available in which aspect extraction and sentiments analysis work together. The research work is *Corresponding Author