A Framework for Users’ Attitude Prediction Based on Visual Features: Application to Movies Recommendations

2018 ◽  
Vol 17 (04) ◽  
pp. 1850037
Author(s):  
Hajer Baazaoui ◽  
Mohamed Ramzi Haddad
Keyword(s):  
Main Idea ◽  
Consumption Patterns ◽  
Visual Features ◽  
Visual Descriptors ◽  
Personal Interests ◽  
Attitude Prediction

Recommendation and personalisation approaches aim to filter the most interesting resources that may attract users’ personal interests and preferences by analysing their past attitudes and consumption patterns. The visual aspect of content constitutes an important factor that drives consumers’ attitudes and decisions. In this context, this work proposes a framework for users’ attitude prediction based on items’ visual descriptors and details one of its possible applications for movies recommendations. The main idea of our proposal is to model users’ interests and consumption behaviors using the movies’ posters images and extract features based on the visual descriptors of the items that they interact with, in order to better predict their attitudes towards the ones they do not know. The recommendation approach was integrated into a movies recommendation application that visually assists users while searching for relevant movies to watch, by finding similar movie posters based on the visual aspects of the poster image.

scholarly journals Regional Approach to Luxury Market Segmentation: The Case Of Western Balkans

2015 ◽  
Vol 1 (5) ◽  
pp. 7-20
Author(s):  
Melika Husic-Mehmedovic ◽  
Emir Agic
Keyword(s):  
Main Idea ◽  
Consumption Patterns ◽  
Market Segment ◽  
Luxury Brands ◽  
Western Balkans ◽  
Luxury Consumption ◽  
Luxury Brand ◽  
Major Transitions ◽  
Post War ◽  
Luxury Market

Nature of the luxury brand requires limited market in order to maintain exclusivity. Individual countries in the Western Balkans are not lucrative per se, therefore, regional segmentation is needed in the case of luxury brands. Countries of Western Balkan, i.e. Bosnia and Herzegovina, Croatia, Serbia and Slovenia are all post-socialist, post-war countries currently going through major transitions. Rather small markets are yet to be established in its final form politically, economically, socially and culturally and individually. Foreign investors and world’s leading companies are concerned mainly about the size of the potential individual market. The main idea of this paper is to analyze luxury consumption in the Western Balkans region in order to identify some consumption patterns and to describe the regional luxury consumer. Broad study among 800 respondents in four countries defines demographics and buying intent of the luxury consumers. Moreover, this study identified luxury consumer region-wide and helps luxury brand managers to target those small countries together as a rather significant market segment of approximately 20.000 consumers. The region that has shared similar historical and cultural facts proved to have similar or the same luxury consumption patterns. This paper has significant practical value for the luxury brand managers and their segmentation of the Western Balkan countries. They will decide much easier to target this region knowing that consumers are sharing the same lifestyle and preferences regarding the luxury consumption. Main limitation of the research is the average income of the sample. However, the top market segment is always difficult to reach with surveys, therefore, qualitative approach might be used in the further studies in this regard.

scholarly journals Unsupervised Selective Rank Fusion on Content-Based Image Retrieval

2019 ◽  
Author(s):  
Lucas Pascotti Valem ◽  
Daniel Carlos Guimarães Pedronette
Keyword(s):  
Image Retrieval ◽  
Visual Information ◽  
Learning Technologies ◽  
Content Based Image Retrieval ◽  
Visual Features ◽  
Machine Learning Methods ◽  
Retrieval Systems ◽  
Visual Descriptors ◽  
Promising Solution ◽  
Distinct Features

Mainly due to the evolution of technologies to store and share images, the growth of image collections have been remarkable for years. Therefore, developing effective methods to index and retrieve such extensive available visual information is indispensable. The CBIR (Content-Based Image Retrieval) systems are one of the main solutions for image retrieval tasks. These systems are mainly supported by the use of different visual descriptors and machine learning methods. Despite the relevant advances in the area, mainly driven by deep learning technologies, accurately computing the similarity between images remains a complex task in various scenarios due to the well known semantic gap problem. As distinct features produce complementary ranking results with different effectiveness performance, a promising solution consists in combining them. However, how to decide which visual features to combine is a very challenging task. This work proposes three novel methods for selecting and combining ranked lists by estimating their effectiveness in an unsupervised way. The approaches were evaluated in five different image collections and several descriptors, achieving results comparable or superior to the state-of-the-art in most of the evaluated scenarios.

Alcohol consumption patterns in heavy drinkers with and without alcoholic liver disease (ALD)

2001 ◽  
Vol 120 (5) ◽  
pp. A117-A117
Author(s):  
K DEAR ◽  
M BRADLEY ◽  
K MCCORMACK ◽  
R PECK ◽  
D GLEESON
Keyword(s):  
Liver Disease ◽  
Alcohol Consumption ◽  
Alcoholic Liver Disease ◽  
Consumption Patterns ◽  
Heavy Drinkers

Reduced change blindness for task-relevant visual features during a social interaction

2001 ◽  
Author(s):  
Donald A. Varakin ◽  
Sheena Rogers ◽  
Jeffrey T. Andre ◽  
Susan L. Davis
Keyword(s):  
Social Interaction ◽  
Change Blindness ◽  
Visual Features

Motivational bases of the development of personal interests and commitments

1971 ◽  
Author(s):  
H. Edward Tryk ◽  
Kenneth J. Appel ◽  
Paul W. McReynolds ◽  
Leonard P. Ullmann ◽  
Ernest R. Hilgard
Keyword(s):  
Personal Interests

Effects of Alcohol Content on Consumption Patterns of Alcoholic Drinks

2007 ◽  
Author(s):  
Philip Terry ◽  
Lorenzo D. Stafford ◽  
Angela S. Attwood ◽  
Stephanie C. Walker ◽  
Suzanne Higgs
Keyword(s):  
Consumption Patterns ◽  
Alcohol Content ◽  
Alcoholic Drinks

ALGEBRA OF PREDICATES AND RELATED GEOMETRIC MODELS CREATION IN REGARDS OF UNIFIED STATE EXAM IN INFORMATICS (RUSSIAN EGE)

2019 ◽  
pp. 40-47
Author(s):  
E. A. Mironchik
Keyword(s):  
Geometric Model ◽  
Main Idea ◽  
Formal Logic ◽  
High Complexity ◽  
Geometric Models ◽  
Complexity Problem ◽  
Logical Expression ◽  
State Examination

The article discusses the method of solving the task 18 on the Unified State Examination in Informatics (Russian EGE). The main idea of the method is to write the conditions of the problem utilizing the language of formal logic, using elementary predicates. According to the laws of logic the resulting complex logical expression would be transformed into an expression, according to which a geometric model is supposed to be constructed which allows to obtain an answer. The described algorithm does allow high complexity problem to be converted into a simple one.

From Freezing to Investing: New Approaches to Monetary and Currency Policies

2008 ◽  
pp. 47-55
Author(s):  
A. Nekipelov ◽  
Yu. Goland
Keyword(s):  
Economic Policy ◽  
Property Rights ◽  
Main Idea ◽  
State Intervention ◽  
Economic Thought ◽  
Human Potential ◽  
Knowledge Based ◽  
Russian Economy ◽  
Knowledge Based Economy

The appeals to minimize state intervention in the Russian economy are counterproductive. However the excessive involvement of the state is fraught with the threat of building nomenclature capitalism. That is the main idea of the series of articles by prominent representatives of Russian economic thought who formulate their position on key elements of the long-term strategy of Russia’s development. The articles deal with such important issues as Russia’s economic policy, transition to knowledge-based economy, basic directions of monetary and structural policies, strengthening of property rights, development of human potential, foreign economic priorities of our state.

PENGARUH MODEL PEMBELAJARAN COOPERATIVE INTEGRATED READING AND COMPOSITION (CIRC) TERHADAP KEMAMPUAN MENENTUKAN IDE POKOK PARAGRAF SISWA KELAS V SD NEGERI 003 PULAU KOPUNG KECAMATAN SENTAJO RAYA KABUPATEN KUANTAN SINGINGI

2019 ◽  
Vol 3 (2) ◽  
Author(s):  
Yuwanda Megri Santika ◽  
Otang Kurniaman ◽  
Zariul Antosa
Keyword(s):  
Main Idea ◽  
Learning Model ◽  
Communication Process ◽  
Fifth Grade ◽  
Control Group ◽  
Control Group Design ◽  
Group Design ◽  
Fifth Grade Students ◽  
Quasi Experimental ◽  
Main Ideas

Reading is one of the important aspects in the communication process. Reading can make someone better understand the contents of the reading. In learning to make it easier for students to understand the contents of the reading it will be easier if it begins with the ability to determine the main ideas of the paragraph. Based on this, the researcher conducted a study by applying the Cooperative Integrated Reading and Composition (CIRC) learning model to the ability to determine the main idea of the paragraph at the fifth grade students of SD 003 Pulau Kopung. This study aims to determine the effect of the CIRC learning model on the ability to determine the main ideas of paragraphs of fifth grade students of SD Negeri 003 Pulau Kopung. This research method is a quasi- experimental Nonequivalent Control Group Design. This research was conducted in two classes, the VA class as the control class and VB class as the experimental class with 22 students in each class. The results of the study showed that the CIRC learning model influenced the ability to determine paragraph main ideas with the results of calculations derived from the gain index, the experimental class using the CIRC learning model got an increase in gain of 0.59 with the middle class and the control class with the normal learning model got an increase of 0.31 with medium class.

Sign in / Sign up

Export Citation Format

Share Document