Interpersonal Influence In Data Mining

1081 Words5 Pages
Abstract For Data Mining works cold start has been a serious problem. Even though we have many algorithms to work on Data Mining , cold start has made people to step back in analyzing the functionality of those algorithms. This lead to little decrease in creativity and optimizations in data mining algorithms. Cold start can be described as unavailability of data for modeling algorithms. With the advent and popularity of social network, more and more users like to share their experiences, such as ratings, reviews, and blogs. The new factors of social network like interpersonal influence and interest based on circles of friends bring opportunities and challenges for recommender system (RS) to solve the cold start and scarcity problem of datasets.…show more content…
Real time Twitter data ranking and recommending articles from a collection of really simple syndication feeds can also be considered as datasets. And one of the conclusions is that users with more friends tend to benefit more. Topic relevance and the social voting process were helpful in providing recommendations. User friends consistently provided better recommendations. For example 90% of users believe the book recommended is good from friends, 75% of users believe that the recommendation is useful from friends. This research shows that the interpersonal influence is important in social media. Some experiments were conducted on large social network in a new form of social media known as micro-blogging. It has a high degree correlation and reciprocity, indicating close mutual acquaintances among users. They had identified different types of user intentions and studied the community structures. Categorizing friends into groups (e.g. family, co-workers) would greatly benefit the adoption of micro-blogging platforms to analyze user intentions. That is to say user intentions or interests can be reflected by those of its…show more content…
This can be correlated to groups of similar interests and training is performed. ContextMF Model includes factors like interpersonal influence and individual preference. Interpersonal influence is mined from previous adopted items. Proposed System In the proposed system we use factors like individual preference, interpersonal influence and interpersonal interest similarity to train datasets. Interpersonal influence can be treated as person buying some items bought by some other people in that circle where he is in or other people he follows. Similarly interpersonal interest circle can be described as people having similar interests. People having similar interests have good chances of buying similar products. In the proposed system we are adding features which are of interest for mining techniques of buying patterns. Advantages Advantage can be described with an example for the feature we have added. Consider 2(A, B) people who are doing BTech. A bought a computer for his academic practices. We can recommend a computer to B considering that they both have similar interest(Here BTech Course). System
Open Document