Build User Profiles Research Articles

Social media and customer behavior analytics for personalized customer engagements

Companies in various industries, including travel, hospitality, and retail, increasingly focus on improving customer relationships and customer loyalty. In this paper, we propose a new systems architecture that combines the textual content in social media messages with product information, such as the descriptions summarized in catalogs, in order to provide marketing campaign recommendations. Companies commonly build user profiles based on purchase histories and other customer-specific information; however, when dealing with social media, we often cannot match the social media users with the customers. In this regard, we address the problem of targeting individual social media messages for which no personalized profile information can be retrieved. Our solution combines two disparate computational toolboxes for text analytics—natural language processing and machine learning—in order to select social media users for whom to target with topic-specific advertisements. Natural language processing is used to analyze the context of social media messages, and machine learning is used to analyze product information, with the goal being to match social media messages to products and ranking potential advertisements. To demonstrate the framework, we detail a real-world application in the travel and tourism industry using Twitter® as the social media platform.

Enriching user profiles using geo-social place semantics in geo-folksonomies

Geo-folksonomies link social web users to geographic places through the tags users choose to label the places with. These tags can be a valuable source of information about the user’s perception of place and can reflect their experiences and activities in the places they label. By analysing the associations between users, places and tags, an understanding of a place and its relationships with other places can be drawn. This place characterisation is unique, dynamic and reflects the perception of a particular user community that generated the geo-folksonomy. In this work, an approach is proposed to analysing geo-folksonomies that builds on and extends existing statistical methods by considering specific concepts of relevance to geographic place resources, namely, place types and place-related activities, and by building a place ontology to encode those concepts and relationships. The folksonomy analysis and evaluation are demonstrated using a realistic geo-folksonomy data set. The resulting ontology is used to build user profiles from the folksonomy. The derived profiles reflect the association between users and the specific places they tag as well as other places with relevant associated place type and activities. The methods proposed here provide the potential for many interesting and useful applications, including the harvesting of useful insight on geographic space and employing the derived user profiles to enhance the search experience and to identify similarities between users based on their association to geographic places.

Geo-Social Profile Matching Algorithm for Dynamic Interests in Ad-Hoc Social Network

Among mobile users, ad-hoc social network (ASN) is becoming a popular platform to connect and share their interests anytime anywhere. Many researchers and computer scientists investigated ASN architecture, implementation, user experience, and different profile matching algorithms to provide better user experience in ad-hoc social network. We emphasize that strength of an ad-hoc social network depends on a good profile-matching algorithm that provides meaningful friend suggestions in proximity. Keeping browsing history is a good way to determine user’s interest, however, interests change with location. This paper presents a novel profile-matching algorithm for automatically building a user profile based on dynamic GPS (Global Positing System) location and browsing history of users. Building user profile based on GPS location of a user provides benefits to ASN users as this profile represents user’s dynamic interests that keep changing with location e.g. office, home, or some other location. Proposed profile-matching algorithm maintains multiple local profiles based on location of mobile device.

An effective news recommendation method for microblog user.

Recommending news stories to users, based on their preferences, has long been a favourite domain for recommender systems research. Traditional systems strive to satisfy their user by tracing users' reading history and choosing the proper candidate news articles to recommend. However, most of news websites hardly require any user to register before reading news. Besides, the latent relations between news and microblog, the popularity of particular news, and the news organization are not addressed or solved efficiently in previous approaches. In order to solve these issues, we propose an effective personalized news recommendation method based on microblog user profile building and sub class popularity prediction, in which we propose a news organization method using hybrid classification and clustering, implement a sub class popularity prediction method, and construct user profile according to our actual situation. We had designed several experiments compared to the state-of-the-art approaches on a real world dataset, and the experimental results demonstrate that our system significantly improves the accuracy and diversity in mass text data.

Personalization Information Retrieval Based on Topic Directory

Personalization information retrieval is very useful in information retrieval system, the user profile can be used to represent the favorites or interests of user. This paper introduces how to automatically learn user interests, build user profiles and re-rank search results.A topic directory method is proposed to calculate the semantic similarity, which takes multi-inheritance into consideration, and then optimize the computing process based on the tree structure of inheritance relationship. Experiments are conducted to compare our method with the popular directory based search methods (e.g., Google Directory Search). Experimental results show that the proposed method in this paper can effectively capture personalization and improve the accuracy of personalized search over existing approaches.

A Multimodal Approach to Incremental User Profile Building

The World Wide Web is the largest distributed information source which is accessed by billions of people all across the world. A unique content so urce on the web can be accessed byvarious users for different purposes. Hence it becomes mandatory tocapture specific information requirements of each user. This paper proposes a multimodal approach to build profile of users in a n incremental manner. The approach proposed in this paper achieves the goal of building user profiles using a hybrid approach. The profile building process is further enriched with the incorporation of web page segmentation technique involving page trees and densitometry. The proposed model extracts the requirement context of the user by utilizing both local and global sources during the profile building process.The experiments conducted on the proposed model confirm the effectiveness of the approach and highlights the channels wh ich carries an edge over others in capturing the user interest.

Mining interests for user profiling in electronic conversations

The increasing amount of Web-based tasks is currently requiring personalization strategies to improve the user experience. However, building user profiles is a hard task, since users do not usually give explicit information about their interests. Therefore, interests must be mined implicitly from electronic sources, such as chat and discussion forums. In this work, we present a novel method for topic detection from online informal conversations. Our approach combines: (i) Wikipedia, an extensive source of knowledge, (ii) a concept association strategy, and (iii) a variety of text-mining techniques, such as POS tagging and named entities recognition. We performed a comparative evaluation procedure for searching the optimal combination of techniques, achieving encouraging results.

Knowledge-based scheme to create privacy-preserving but semantically-related queries for web search engines

Web search engines (WSEs) are basic tools for finding and accessing data in the Internet. However, they also put the privacy of their users at risk. This happens because users frequently reveal private information in their queries. WSEs gather this personal data and build user profiles which are used to provide personalized search (PS). PS improves the users’ search results and, hence, it is a key element for the successfulness of WSEs: the entity that offers the best searching experience should attract more users. Nevertheless, profiles can also be used in an improper way by WSEs or they can be stolen by attackers. This situation requires privacy-preserving schemes able to handle from simple queries (one single term) to complex queries (several words with or without relation). Generally, these systems generate and submit inaccurate queries in order to provide privacy, but these queries must be carefully built in order to keep the usefulness of the user profiles. Current literature does not address the generation of privacy-preserving and useful complex queries. Therefore, this paper presents a new scheme that generates distorted user queries from a semantic point of view in order to preserve the usefulness of user profiles. Besides, linguistic analysis techniques are used to properly interpret complex queries performed by users and generate new semantically-related ones accordingly. The performance of the new scheme is evaluated in terms of semantic preservation of new queries, privacy level and runtime. A set of query logs taken from real users and compiled by AOL is used as test data.

An automatic HTTP cookie management system

HTTP cookies have been widely used for maintaining session states, personalizing, authenticating, and tracking user behaviors. Despite their importance and usefulness, cookies have raised public concerns on Internet privacy because they can be exploited by third-parties to track user behaviors and build user profiles. In addition, stolen cookies may also incur severe security problems. However, current Web browsers lack secure and convenient mechanisms for cookie management. A cookie management scheme, which is easy-to-use and has minimal privacy risk, is in great demand; but designing such a scheme is a challenge. In this paper, we conduct a large scale HTTP cookie measurement and introduce CookiePicker, a system that can automatically validate the usefulness of cookies from a Web site and set the cookie usage permission on behalf of users. CookiePicker helps users achieve the maximum benefit brought by cookies, while minimizing the possible privacy and security risks. We implement CookiePicker as an extension to Firefox Web browser, and obtain promising results in the experiments.

Preface to the special issue on data mining for personalization

The continued growth and proliferation of e-commerce, online services, and Webbased information systems, has led to an explosion of available content and resources in digital form. As a result of user interactions with these resources, tremendous volumes of clickstream, transaction, and user data are collected by organizations in their daily operations. Mining and analyzing such data can help these organizations determine the life time value of clients, design cross marketing strategies across products and services, evaluate the effectiveness of targeted promotional campaigns, and thus provide more effective personalized content to visitors. Automatic personalization is a central technology used in user-adaptive systems to deliver dynamic content, such as textual information, links, advertisements, and product recommendations that are tailored to the needs and interests of a particular user or a segment of users. The process of personalization comprises iterative invocations of the personalization cycle consisting of the stages of understanding the user and building user profiles and models; delivering personalized offerings to the users based on this understanding; measuring impacts of these offerings on the users; and adjusting all the previous stages based on the measured feedback. Data mining is one of the key technologies used in various stages of this personalization process, especially in building user models and delivering personalized offerings to the users. Therefore, it is crucial to develop appropriate data mining methods fitting the corresponding personalization tasks well. This special issue of User Modeling and User-Adapted Interaction explores recent developments and applications of data mining and machine learning techniques in

Speech-Enabled Tools for Augmented Interaction in E-Learning Applications

This article presents systems that use speech technology, to emulate the one-on-one interaction a student can get from a virtual instructor. A web-based learning tool, the Learn IN Context (LINC+) system, designed and used in a real mixed-mode learning context for a computer (C++ language) programming course taught at the Université de Moncton (Canada) is described here. It integrates an Internet Voice Searching and Navigating (IVSN) system that helps learners to search and navigate both the web and their desktop environment through voice commands and dictation. LINC+ also incorporates an Automatic User Profile Building and Training (AUPB&T) module that allows users to increase speech recognition performance without having to go through the long and fastidious manual training process. The findings show that the majority of learners seem to be satisfied with this new media, and confirm that it does not negatively affect their cognitive load.

Employing Latent Dirichlet Allocation for fraud detection in telecommunications

Fraud detection in the telecommunications industry requires the identification of a small fraction of fraudulent calls from the high volume of call traffic. This presents a significant research challenge in the design of efficient and effective algorithms to combat telecommunications fraud. This paper employs Latent Dirichlet Allocation (LDA) to build user profile signatures and assumes that any significant unexplainable deviations from the normal activity of an individual user is strongly correlated with fraudulent activity. The user activity is represented as a probability distribution over call features which surmises the user’s calling behaviour. This probability distribution is derived from LDA which can accurately describe user profiles by combining different classes of distributions. To score calls we compare the likelihood of the user generating a call versus a fraudster generating the same call. Our experiments demonstrate that using such a probability distribution and employing even a rough profile of a fraudster’s activity ameliorates the detection of fraudulent calls. Our method is computationally efficient and can scale up to a realistic real time detection.

Multimedia content modeling and personalization

There's a wealth of possiblities in the realm of personalized multimedia. Personalizing multimedia content, however, is an extensive process that involves extracting and modeling semantic and structural information about the content as well as metadata; building user profiles either manually or automatically through direct obersvation of user behavior; retrieving and filtering content through the user profiles; and adapting the filtered content to fit usage conditions and user preferences.