Basics of Content-based Recommender

Systems
Prepared By
Senthil.V
Content-based Recommender:
 Systems implementing a content-based recommendation
approach analyze a set of documents and/or descriptions of
items previously rated by a user, and build a model or profile of
user interests based on the features of the objects rated by that
user.
 The profile is a structured representation of user interests,
adopted to recommend new interesting items. The
recommendation process basically consists in matching up the
attributes of the user profile against the attributes of a content
object.
 The re-sult is a relevance judgment that represents the user’s
level of interest in that object. If a profile accurately reflects user
preferences, it is of tremendous advantage for the effectiveness
of an information access process.
 For instance, it could be used to filter search results by deciding
whether a user is interested in a specific Web page or not and, in
the negative case, preventing it from being displayed.
A High Level Architecture of Content-based Systems:

Content-based Information Filtering (IF) systems need proper

techniques for repre-senting the items and producing the user
profile, and some strategies for comparing the user profile with the
item representation.
The high level architecture of a content-based recommender
system is depicted in Figure 3.1. The recommendation process is
performed in three steps, each of which is handled by a separate
component:
CONTENT ANALYZER:
 When information has no structure (e.g. text), some kind of pre-
processing step is needed to extract structured relevant
information.
 The main responsibility of the component is to represent the
content of items (e.g. documents, Web pages, news, product
descriptions, etc.) coming from in-formation sources in a form
suitable for the next processing steps.
 Data items are analyzed by feature extraction techniques in
order to shift item representation from the original information
space to the target one (e.g. Web pages represented as
keyword vectors).
PROFILE LEARNER:
This module collects data representative of the user prefer-
ences and tries to generalize this data, in order to construct the
user profile. Usu-ally, the generalization strategy is realized
through machine learning techniques, which are able to infer a
model of user interests starting from items liked or disliked in the
past.For instance, the PROFILE LEARNER of a Web page recom-
mender can implement a relevance feedback method in which the
learning technique combines vectors of positive and negative
examples into a prototype vector representing the user
profile.Training examples are Web pages on which a positive or
negative feedback has been provided by the user;
FILTERING COMPONENT
 This module exploits the user profile to suggest rel-evant items
by matching the profile representation against that of items to be
recommended.
 The result is a binary or continuous relevance judgment (com-
puted using some similarity metrics), the latter case resulting in a
ranked list of potentially interesting items. In the above
mentioned example, the matching is realized by computing the
cosine similarity between the prototype vector and the item
vectors.
working process
 The first step of the recommendation process is the one
performed by the CON-TENT ANALYZER, that usually borrows
techniques from Information Retrieval sys-tems.
 Item descriptions coming from Information Source are processed
by the CONTENT ANALYZER, that extracts features (keywords,
n-grams, concepts, . . . ) from unstructured text to produce a
structured item representation, stored in the repository
Represented Items.
 In order to construct and update the profile of the active user ua
(user for which recommendations must be provided) her
reactions to items are collected in some way and recorded in the
repository Feedback.
 These reactions, called anno-tations or feedback, together with
the related item descriptions, are exploited during the process of
learning a model useful to predict the actual relevance of newly
presented items. Users can also explicitly define their areas of
interest as an initial profile without providing any feedback.
 Typically, it is possible to distinguish between two kinds of
relevance feedback: positive information (inferring features liked
by the user) and negative information (i.e., inferring features the
user is not interested in).
 Two different techniques can be adopted for recording user’s
feedback. When a system requires the user to explicitly evaluate
items, this technique is usually re-ferred to as “explicit feedback”;
 the other technique, called “implicit feedback”,does not require
any active user involvement, in the sense that feedback is
derived from monitoring and analyzing user’s activities.
 Explicit evaluations indicate how relevant or interesting an item
is to the user. There are three main approaches to get explicit
relevance feedback:
 like/dislike: items are classified as “relevant” or “not relevant” by
adopting a simple binary rating scale, such as in [12];
 ratings: a discrete numeric scale is usually adopted to judge
items, such as in[86].Alternatively, symbolic ratings are mapped
to a numeric scale, such as in Syskill & Webert [70], where users
have the possibility of rating a Web page as hot, lukewarm, or
cold;
 text comments : Comments about a single item are collected and
presented to the users as a means of facilitating the decision-
making process, such as in . For instance, customer’s feedback
at Amazon.com or eBay.com might help users in deciding
whether an item has been appreciated by the community.
 Textual comments: are helpful, but they can overload the active
user because she must read and interpret each comment to
decide if it is positive or negative, and to what de-gree.
 The literature proposes advanced techniques from the affective
computing research area to make content-based
recommenders able to automatically perform this kind of
analysis.
 Explicit feedback has the advantage of simplicity, albeit the
adoption of nu-meric/symbolic scales increases the cognitive
load on the user, and may not be adequate for catching user’s
feeling about items.
 Implicit feedback: methods are based on assigning a relevance
score to specific user actions on an item, such as saving,
discarding, printing, bookmarking, etc.
 The main advantage is that they do not require a direct user
involvement, even though biasing is likely to occur, e.g.
interruption of phone calls while reading.
 In order to build the profile of the active user ua, the training set
T Ra for ua must be defined. T Ra is a set of pairs Ik, rk , where
rk is the rating provided by ua on the item representation Ik.
 Given a set of item representation labeled with ratings, the
PROFILE LEARNER applies supervised learning algorithms to
generate a predictive model – the user profile – which is usually
stored in a profile repository for later use by the FILTERING
COMPONENT.
 Given a new item representation, the FIL-TERING
COMPONENT predicts whether it is likely to be of interest for the
active user, by comparing features in the item representation to
those in the representation of user preferences (stored in the
user profile).
 Usually, the FILTERING COMPO-NENT implements some
strategies to rank potentially interesting items according to the
relevance with respect to the user profile.Top-ranked items are
included in a list of recommendations La, that is presented to ua.
 User tastes usually change in time, therefore up-to-date
information must be maintained and provided to the PRO-FILE
LEARNER in order to automatically update the user profile.
Further feedback is gathered on generated recommendations by
letting users state their satisfaction or dissatisfaction with items
in La.
 After gathering that feedback, the learning process is performed
again on the new training set, and the resulting profile is adapted
to theupdated user interests. The iteration of the feedback-
learning cycle over time allows the system to take into account
the dynamic nature of user preferences.
Thank You