Denis Kotkov

Denis Kotkov
University of Helsinki | HY

Doctor of Philosophy

About

18
Publications
20,120
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
411
Citations
Citations since 2016
17 Research Items
411 Citations
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100
Introduction

Publications

Publications (18)
Conference Paper
Full-text available
Content-based and hybrid recommender systems rely on item-tag ratings to make recommendations. An example of an item-tag rating is the degree to which the tag "comedy" applies to the movie "Back to the Future (1985)". Ratings are often generated by human annotators who can be inconsistent with one another. However, many recommender systems take ite...
Conference Paper
Full-text available
Attaching tags to items, such as books or movies, is found in many online systems. While a majority of these systems use binary tags, continuous item-tag relevance scores, such as those in tag genome, offer richer descriptions of item content. For example, tag genome for movies assigns the tag "gangster" to the movie "The Godfather (1972)" with a s...
Conference Paper
Full-text available
Traditionally, recommender systems provide a list of suggestions to a user based on past interactions with items of this user. These recommendations are usually based on user preferences for items and are usually generated with a delay. Critiquing recommender systems allow users to provide immediate feedback to recommendations with tags and receive...
Article
Full-text available
Most recommender systems suggest items that are popular among all users and similar to items a user usually consumes. As a result, the user receives recommendations that she/he is already familiar with or would find anyway, leading to low satisfaction. To overcome this problem, a recommender system should suggest novel, relevant and unexpected i.e....
Conference Paper
Most recommender algorithms are designed to suggest relevant items, but suggesting these items does not always result in user satisfaction. Therefore, the efforts in recommender systems recently shifted towards serendipity, but generating serendipitous recommendations is difficult due to the lack of training data. To the best of our knowledge, ther...
Conference Paper
Full-text available
Over the past several years, research in recommender systems has emphasized the importance of serendipity, but there is still no consensus on the definition of this concept and whether serendipitous items should be recommended is still not a well-addressed question. According to the most common definition, serendipity consists of three components:...
Conference Paper
Full-text available
Cross-domain recommender systems use information from source domains to improve recommendations in a target domain, where the term domain refers to a set of items that share attributes and/or user ratings. Most works on this topic focus on accuracy but disregard other properties of recommender systems. In this paper, we attempt to improve serendipi...
Conference Paper
The purpose of this paper is to explore the participation of main actors in Facebook. The engagement shows different degrees of participation that directly affect the brand image and reputation. This research applies Situational Crisis Communication Theory (SCCT) to interaction in the social media. It provides possibilities for decision makers to m...
Article
Full-text available
in open access available at http://redfame.com/journal/index.php/smc/article/view/1746/1858
Article
Full-text available
Recommender systems use past behaviors of users to suggest items. Most tend to offer items similar to the items that a target user has indicated as interesting. As a result, users become bored with obvious suggestions that they might have already discovered. To improve user satisfaction, recommender systems should offer serendipitous suggestions: i...
Conference Paper
Full-text available
Online social networks have become an essential part of our daily life, and an increasing number of users are using multiple online social networks simultaneously. We hypothesize that the integration of data from multiple social networks could boost the performance of recommender systems. In our study, we perform cross-social network collaborative...

Network

Cited By

Projects

Projects (3)
Project
Location-based social networks have attracted the interest of millions of users who can now not only connect and interact with their friends, as in the case of traditional online social networks, but can share their whereabouts in real time exploiting GPS sensors embedded in smartphones with Internet connectivity. Real world places are a core entity of location-based social networks and as users transit between them, urban mobility is represented with unprecedented richness in terms of geographic scale and spatial granularity. As a consequence, location-based services offer new opportunities in the space of mobile applications, but also the potential to allow large-scale empirical validation of theories of human movement. However, this new data paradigm comes with the sparsity that is a direct consequence of the heavy-tailed distributions characterizing user activity in online social services. This project aims at performing an analysis of millions of user movements in metropolitan areas around the world.
Archived project
Mining Social Media, a project funded by the Academy of Finland, running 2013-2017. Budget 700000 euro.