E-business is an increasingly pervasive element of ambient intelligence. Ambient intelligence promotes the user-centered system where as per the feedback of user, the system changes itself to facilitate the transmission and marketing of goods and information to the appropriate e-business market. Ambient Intelligence ensures that the e-business activities generate good confidence level among the customers. The confidence occurs when the customers feel that the product can be relied upon to act in their best interest and knowledge. It affects the decision that whether a customer decides to buy the product or not.
In e-business there are various customers, makes different types of comment, opinions about the products, services etc. These comments are may be in favor or in against of the products or services, this can be recognized by the help of the part of speech tagging method in which the adjectives and the negative words (no, not etc) is used for the comment summarization.
The existing algorithm is important as the number of comments increases because it is an unsupervised method so there are no comparisons between input and output. With the growth of internet there are many products are sold on the web. Some products can have thousand of comments many of them are very easy to understand but few of them are very difficult to understand their sentiment and opinion.
For this the method was developed that can analyze and summarize the customers opinion and comments about the by extracting frequent, infrequent and mining & extracting the opinion words.
Four steps are used-
‘ Part of speech tagging
‘ Extracting frequent aspects of products
‘ Extracting infrequent aspects of products
‘ Mining and identifying opinion words
3.2 WORK TO BE DONE
According to works done so far customer can comment or express their views on the various of blogging sites by the use of opinion mining, but the expressed comments cannot be recognized properly and the best opinion cannot be optimized which can be help full for decision making purpose.
If customer express their views about any product or services which are provided by the business organization so it should be analyzed and recognized properly that whether the comment is in favor or against the product .
The dissertation is about the developing the intelligent technique to analyze the implicit aspects of the opinion mining and extending the work of summarization of the customers views by more refinement of the customers opinion about the product.
‘ The explosive increase in Internet usage has attracted technologies for automatically mining the user generated contents (UGC) from Web documents. These UGC-rich resources have raised new opportunities and challenges to carry out the opinion extraction and mining tasks for opinion summaries. The technology of opinion extraction allows users to retrieve and analyze people’s opinions scattered over Web documents. Opinion mining is a process which is concerned with the opinions generated by the consumers about the product.
Opinion Mining aims at understanding, extraction and classification of opinions scattered in unstructured text of online resources. The search engines performs well when one wants to know about any product before purchase, but the filtering and analysis of search results often complex and time consuming. This generated the need of intelligent technologies which could process these unstructured online text documents through automatic classification, concept recognition, text summarization, etc. These tools are based on traditional natural language techniques, statistical analysis, and machine learning techniques.
The summarization and analysis of the customer comment is done with the help of the part of speech tagging and various types of grammatical terms. The accuracy of analysis improves with the increase in the number of comments. As the comments increases the comparison between the comments will become easier for merchants and any business bodies. Computer cannot understand the implicit aspects of the opinion so; this intelligent technique will help to overcome this problem of summarizing the customers review in e-business techniques.
‘ In the extension of the previous work the new approach is to find the implicit aspects of the sentence by which the comments which do not specify their sentiments or opinion can be properly analyzed and after the orientation checking knowledge formation or the identifying the opinion words which tells that the comments is in favor or not.
‘ In the FSS algo the frequent items are identified and the sentiments which are the implicit aspects of the customer comment will be analyzed by the help of NLP, by the help of this the sentiment can be summarized as the other customer and the business bodies can understand the opinions of the others easily and make their decisions efficiently.
‘ n FSS the enhancement in the previous work has been done the we can identifies the neutral comments as well as positive and negative comments of the customers which do not shows their true opinions by the comments, by the help of this it becomes easy for the viewers to judge.