hi am vishnu, please give information about Automatic machine for Project

Social media has enabled web users to interact
through social platforms, express their opinions,
comment and review various products/items.
Such user-generated content has been analysed
from a social as well as content-oriented point
of view. For instance, social network analysis
techniques have been used to identify user roles
(Agarwal et al., 2008; Domingos and Richardson,
2001; Fisher et al., 2006; Zhang et al.,
2007) and text or opinion mining techniques have
been applied to identify positive/negative tendencies
within user online review comments (Ding
and Liu, 2007; Ghose et al., 2007; Hu and Liu,
2004; Leskovec et al., 2010). In the applicative
context, recommender systems (Adomavicius and
Tuzhilin, 2005) make use of the opinion information
(such as in star-rating systems) and recommend
items (movies, products, news articles, etc.)
or social elements (i.e. propositions to connect
with other people or communities), that are likely
to be of interest to a specific user.
Typically, a recommender system compares a
user profile with some reference characteristics,
and seeks to predict the “preference” or “rating”
that a user would give to an item not yet considered.
These characteristics may be part of the information
item (the content-based approach) or
the user’s social environment (the collaborative
filtering approach). Comments published on social
networking or review web sites are sometimes
used by recommender systems (Aciar et al., 2007;
Jakob et al., 2009) in order to find out similarities
between users that comment on the same items
in the same way. However, extracting explicit semantic
information carried out in these comments
(e.g. “this printer is slow”) is of great interest in
order to detect what a user has liked or disliked
about a given topic (e.g. the speed of the printer)
and consequently take it into account to make recommendations.
In this paper, we propose the extraction of opinions
and suggestions from user reviews or free
text and their use as input information to improve
recommender systems. This technique could be
used on top of standard recommender techniques
in order to further fine-grain the recommendation
according to the user comments.