Movie Recommendation System Research Articles

Understanding the Effects of Explanation Types and User Motivations on Recommender System Use

It is becoming increasingly common for intelligent systems, such as recommender systems, to provide explanations for their generated recommendations to the users. However, we still do not have a good understanding of what types of explanations work and what factors affect the effectiveness of different types of explanations. Our work focuses on explanations for movie recommender systems. This paper presents a mixed study where we hypothesize that the type of explanation, as well as user motivation for watching movies, will affect how users respond to recommendation system explanations. Our study compares three types of explanations: i) neighbor-ratings, ii) profile-based, and iii) event-based, as well as three types of user movie-watching motivations: i) hedonic (fun and relaxation), ii) eudaimonic (inspiration and meaningfulness), and iii) educational (learning new content). We discuss the implications of the study results for the design of explanations for movie recommender systems, and future novel research directions that the study results uncover.

Deep-Reinforcement-Learning-Based User Profile Perturbation for Privacy-Aware Recommendation

User profile perturbation protects privacy in the release of user profiles to receive recommendation services, in which the privacy budget as a privacy parameter can be controlled to effect a tradeoff between the recommendation quality and privacy protection against inference attacks. In this article, we propose a deep reinforcement learning (RL)-based user profile perturbation scheme for recommendation systems. This scheme applies differential privacy to protect user privacy and uses deep RL to choose the privacy budget against inference attackers. Based on an evaluated neural network (NN) and a target NN, this scheme enables a user device to optimize the privacy budget over time based on the sensitivity level of the clicked item, the similarities among the recommended items, and the estimated privacy loss. We provide an upper bound on the privacy protection performance of this scheme in the recommendation game and evaluate its computational complexity. Simulation results for a movie recommendation system show that this scheme increases the user privacy protection level for a given recommendation quality compared with benchmark schemes.

Long Short-Term Memory Based Movie Recommendation

Recommender systems (RS) have become a fundamental tool for helping users make decisions around millions of different choices nowadays – the era of Big Data. It brings a huge benefit for many business models around the world due to their effectiveness on the target customers. A lot of recommendation models and techniques have been proposed and many accomplished incredible outcomes. Collaborative filtering and content-based filtering methods are common, but these both have some disadvantages. A critical one is that they only focus on a user's long-term static preference while ignoring his or her short-term transactional patterns, which results in missing the user's preference shift through the time. In this case, the user's intent at a certain time point may be easily submerged by his or her historical decision behaviors, which leads to unreliable recommendations. To deal with this issue, a session of user interactions with the items can be considered as a solution. In this study, Long Short-Term Memory (LSTM) networks will be analyzed to be applied to user sessions in a recommender system. The MovieLens dataset is considered as a case study of movie recommender systems. This dataset is preprocessed to extract user-movie sessions for user behavior discovery and making movie recommendations to users. Several experiments have been carried out to evaluate the LSTM-based movie recommender system. In the experiments, the LSTM networks are compared with a similar deep learning method, which is Recurrent Neural Networks (RNN), and a baseline machine learning method, which is the collaborative filtering using item-based nearest neighbors (item-KNN). It has been found that the LSTM networks are able to be improved by optimizing their hyperparameters and outperform the other methods when predicting the next movies interested by users.

A review of movie recommendation system: Limitations, Survey and Challenges

Recommendation System is a major area which is very popular and useful for people to take proper decision. It is a method that helps user to find out the information which is beneficial for the user from variety of data available. When it comes to Movie Recommendation System, recommendation is done based on similarity between users (Collaborative Filtering) or by considering particular user’s activity (Content Based Filtering) which he wants to engage with. So to overcome the limitations of collaborative and content based filtering generally, combination of collaborative and content based filtering is used so that a better recommendation system can be developed. Also various similarity measures are used to find out similarity between users for recommendation. In this paper, we have reviewed different similarity measures. Various companies like face book which recommends friends, LinkedIn which recommends job, Pandora recommends music, Netflix recommends movies, Amazon recommends products etc. use recommendation system to increase their profit and also benefit their customers. This paper mainly concentrates on the brief review of the different techniques and its methods for movie recommendation, so that research in recommendation system can be explored.

Evaluation Of Recommendation System On A Movie Dataset

Evaluation Of Recommendation System On A Movie Dataset

A novel hybrid approach towards movie recommender systems

Collaborative and content-based filtering are the majorly used approaches towards implementing recommender systems which can successfully predict the item(s) to be recommended to users based upon their preferences. Each of the methods has its own advantages and disadvantages that are specific to the situation they are used in. The hybrid approach aims to combine both techniques in multiple ways to optimize results and overcome shortcomings. In this paper, we propose a hybrid approach based recommendation engine to improve accuracy. While content based recommendations are made on the similarity of items’ attributes, collaborative recommendations are based on similarity of users. Collaborative filtering is achieved by matrix factorization technique. One of the most effective algorithms for matrix factorization: Singular Value Decomposition (SVD) has been used to perform collaborative filtering and combined with content based model to predict the item ratings per user. The paper aims to achieve the final result with minimum possible errors as per user preferences and recommended items.

Personalized Standard Deviations Improve the Baseline Estimation of Collaborative Filtering Recommendation

Baseline estimation is a critical component for latent factor-based collaborative filtering (CF) recommendations to obtain baseline predictions by evaluating global deviations for both users and items from personalized ratings. Classical baseline estimation presupposes that the user’s factual rating range is the same as the system’s given rating range. However, from observations on real datasets of movie recommender systems, we found that different users have different actual rating ranges, and users can be classified into four kinds according to their personalized rating criterion, including normal, strict, lenient, and middle. We analyzed ratings’ distributions and found that the proportion of user ratings’ local standard deviation to the system’s global standard deviation is equal to that of the user’s actual rating range to the system’s rating range. We propose an improved and unified baseline estimation model based on the standard deviation’s proportion to alleviate the influence of classical baseline estimation’s limitation. We also apply the proposed baseline estimation model in existing latent factor-based CF recommendations and propose two instances. We performed experiments on full ratings of datasets by cross evaluations, including Flixster, Movielens (10 M), Movielens (latest small), FilmTrust, and MiniFilm. The results prove that the proposed baseline estimation model has better predictive accuracy than the classical model and is efficient in improving prediction performance for existing latent factor-based CF recommendations.

A STUDY ON MOVIE RECOMMENDER SYSTEMS BASED ON WORDPRESS PLATFORM

The rapid growth of data collection has led to a new era of information. Data is being used to create more efficient systems and this is where Recommendation Systems come into play. Recommender systems are among the most effcient tools for information filtering to improve the quality of search results and provide items that are more relevant to the search item or are realted to the search history of the user, especially from big data on Internet. Among those, movie recommendation systems are the useful tools to assist users in classifying them with similar interests. This makes them a central part of websites and e-commerce applications. This paper aims to describe the implementation of a movie recommender system built on the Wordpress platform to be able to take advantage of the plugin support system and outstanding management and statistical features. The obtained results indicate that the proposed approach may provide high performance regarding reliability, efficiency, and accuracy. Moreover, the user-friendly interface and suitable display for devices ranging from desktop to mobile devices are also the advantages.

MOVIE RECOMMENDATION SYSTEM USING ITEM BASED COLLABORATIVE FILTERING

In today's digital world where there is an endless variety of content consumed such as books, videos, articles, Films, etc., finding material of one's choice has become an infallible task. Digital content on the other hand Providers want to engage more and more users in their service for maximum time. Where is it the recommender system comes into picture where content providers advise users by content User choice in this paper we have proposed a movie recommendation system .Purpose of movie recommendation system aims to provide users with accurate movie recommendations. Usually basic recommendation system to make recommendations consider one of the following factors; User preference known as content based Filtering or the preference of similar users known as collaborative filtering. To create a stable and accurate recommender system will use of content based filtering.

A Novel Rule based Data Mining Approach towards Movie Recommender System

The proposed research work is an effort to provide accurate movie recommendations to a group of users with the help of a rule-based content-based group recommender system. The whole approach is categorized into 2 phases. In phase 1, a rule- based approach has been proposed which considers the users’ viewing history to provide the Rule Base for every individual user. In phase 2, a novel group recommendation system has been proposed which considers the ratings of the movies as per the rule base generated in phase 1. Phase 2 also considers the weightage of every individual member of the group to provide the accurate movie recommendation to that particular group of users. The results of experimental setup also establish the fact that the proposed system provides more accurate outcomes in terms of precision and recall over other rule learning algorithms such as C4.5.

MOVIE RECOMMENDATION SYSTEM

In this digital era that we live in, Recommendation systems have become a part and parcel of our everyday lives. There are tons of options out there for everything that we do and people might find themselves in a difficult place while making a choice, ‘a perfect one!’ This is where the Recommendation Systems step in. Internet Giants such as Amazon, Netflix, YouTube, Spotify, Facebook etc can be seen using these technologies to keep their audience interested. So, through this work, we attempt to build a simple movie recommendation system employing the famous technique‘User-User Collaborative Filtering’ and design a GUI for the same.

Social movie recommender system based on deep autoencoder network using Twitter data

Recommender systems attempt to provide effective suggestions to each user based on their interests and behaviors. These recommendations usually match the personal user preferences and assist them in the decision-making process. With the ever-expanding growth of information on the web, online education systems, e-commerce, and, eventually, the emergence of social networks, the necessity of developing such systems is unavoidable. Collaborative filtering and content-based filtering are among the most important techniques used in recommender systems. Meanwhile, with the significant advances in deep learning in recent years, the use of this technology has been widely observed in recommender systems. In this study, a hybrid social recommender system utilizing a deep autoencoder network is introduced. The proposed approach employs collaborative and content-based filtering, as well as users’ social influence. The social influence of each user is calculated based on his/her social characteristics and behaviors on Twitter. For the evaluation purpose, the required datasets have been collected from MovieTweetings and Open Movie Database. The evaluation results show that the accuracy and effectiveness of the proposed approach have been improved compared to the other state-of-the-art methods.

Implementation of Movie Recommendation System Using Machine Learning

As world is evolving, similarly people's desire, trend, interests are also changing. Same way even in the field of movies, people want to watch the movies according to their interest. Many web-based movie service providers have emerged and to increase their business and popularity, they want to keep their subscribers entertained. To improve their business, the service provider should recommend movies which users might like, so that they might watch another movie and be entertained. By doing this there is high possibility that customers will periodically renew the web-based movie service provider application. The objective of this project is to implement the machine learning based movie recommendation system which can recommend the movies to the users based on their interest and ratings. To achieve this, content-based filtering is used to recommend movie based on movie-movie similarity, collaborative based filtering is used to compute features based on user information and movie information. The proposed system uses the new ensemble learning algorithm, XGBoost algorithm to improve the performance. The results show that the proposed system is effective for movie recommendation and the system minimizes the root mean square error (RMSE).

Towards Personalized Movie Selection for Wellness: Investigating Event-Inspired Movies

ABSTRACT Movie recommender systems help users to navigate the magnitude and diversity of movies that people have easy access to nowadays, especially with online streaming services. However, current systems personalize recommendations primarily based on what they think a specific user would like or prefer using information about how similar the users are to other users. Prior work has suggested that this could lead to a ‘filter bubble’ whereby users only watch movies that they are comfortable with. This paper presents the novel concept of event-inspired movies that draw on users’ highly specific everyday life experiences to recommend movies that are meaningful to them. To conduct the study, we developed a systematic process to align movies with viewer variables. Meaningful movies have been said to have therapeutic potential to possibly affect one’s sense of overall well-being. We conducted a study with 24 participants to explore how users engage with event-inspired movies, whether event-inspired movies are perceived as more relevant, and their potential to affect users’ sense of life satisfaction. In so doing, we also contribute a process and insights on how to operationalize event-inspired movies that can inform the implementation of a movie recommender system situated within the proposed paradigm.

Movie Recommendation Based on Posters and Still Frames using Machine Learning

Movie recommendation system has become a key part in online movie services to gain and maintain the huge market. While within the preceding studies works Convolution neural network (CNN) concept is employed to spot the various movies with similar posters or stills to recommend the users. Using CNN, similar posters and stills are classified into group and any hard cash within the poster may place it out of the group. But the CNN method isn't fully connected and uses backpropagation technique which could be a touch slow within the poster identification and more over just with posters the films cannot be of comparable one and should disappoint the user. Technologies like Fully Convoluted neural network (FCN) makes use of Convolution neural network concept by connecting all neural networks and adding filters and pooling layer in between each filter layer. Data Augmentation is an algorithm which helps in increasing accuracy for the predicting movies. LASSO regression is employed to get images of high multicollinearity. Soft-max layer is employed to work out the probability of the similarities int poster to create it more appropriate for the user. K-means clustering is employed to classify the films still further to recommend thes implest movietotheuser.

Movie Recommendation System Based on Users’ Personal Information and Movies Rated Using the Method of k-Clique and Normalized Discounted Cumulative Gain

Movie Recommendation System Based on Users’ Personal Information and Movies Rated Using the Method of k-Clique and Normalized Discounted Cumulative Gain

User Based Collaborative F ltering w ith Recursive Neural Network Prediction Model

Nowadays, with the enormous volume of online data, more consideration has been given to develop information driven recommender systems (RSs). Those schemes automatically guide consumers to discover services or movie with regard to their own interests from a huge set of possible choices. Most RS are employed to recommend the user based on their ratings and their preferences. Hence the existing RS provides very narrow recommendations and it restrict the user from accessing the different products. In this paper a novel Movie Recommender System with Cosine Similarity based Collaborative filtering and Recursive neural network MRS-CCR is proposed to the users based on the movie ratings. In the proposed RS the cosine similarity is utilized for determining the similarity among the users over the rated movies, which is employed to predict the rating of the unrated movie for each user through collaborative filtering. The Collaborative filtering (CF) is more successful recommendation methods because of its simplicity and accuracy. In the present work, matrix factorization technique is used for collaborative filtering. The obtained outcome of collaborative filter is fed into the Recursive neural network which is based on tanh activation function. The Recursive neural network predicts the recommended movies to the user. The outcome of the Recursive neural network is used for constructing the confusion matrix for evaluation. The experimental outcome of MRS-CCR is related to existing system on error and accuracy metrics. The proposed MRS-CCR has the accuracy of 95.53% better than the existing RS.

Movie recommendation system using machine learning

Nowadays, the recommendation system has made finding the things easy that we need. Movie recommendation systems aim at helping movie enthusiasts by suggesting what movie to watch without having to go through the long process of choosing from a large set of movies which go up to thousands and millions that is time consuming and confusing. In this article, our aim is to reduce the human effort by suggesting movies based on the user’s interests. To handle such problems, we introduced a model combining both content-based and collaborative approach. It will give progressively explicit outcomes compared to different systems that are based on content-based approach. Content-based recommendation systems are constrained to people, these systems don’t prescribe things out of the box, thus limiting your choice to explore more. Hence, we have focused on a system that resolves these issues.

Analyzing emotion based movie recommender system using fuzzy emotion features

User generated contents like reviews and comments contain both the information about a given product and also the opinions asserted by the user. With the surge in internet usage, there is a cascade of user generated data such a reviews and comments. People share their experiences, opinions, sentiments and emotions by writing reviews and comments for products they purchase online or after watching a movie, reading books etc. These user generated data contains emotion lexicons such as happiness, sadness, and surprise. Analysis of such emotion can provide a new aspect for recommending new items based on their emotional preferences. In this work, we extract the emotions from this user generated data using the lexical ontology, WordNet and information from the domain of psychology. These extracted emotions can be used for recommendations. Evaluation on emotion prediction further verifies the effectiveness of the proposed model in comparison to traditional rating based item similarity model. We further compare this with fuzziness in emotion features.

Design of an Unsupervised Machine Learning-Based Movie Recommender System

This research aims to determine the similarities in groups of people to build a film recommender system for users. Users often have difficulty in finding suitable movies due to the increasing amount of movie information. The recommender system is very useful for helping customers choose a preferred movie with the existing features. In this study, the recommender system development is established by using several algorithms to obtain groupings, such as the K-Means algorithm, birch algorithm, mini-batch K-Means algorithm, mean-shift algorithm, affinity propagation algorithm, agglomerative clustering algorithm, and spectral clustering algorithm. We propose methods optimizing K so that each cluster may not significantly increase variance. We are limited to using groupings based on Genre and Tags for movies. This research can discover better methods for evaluating clustering algorithms. To verify the quality of the recommender system, we adopted the mean square error (MSE), such as the Dunn Matrix and Cluster Validity Indices, and social network analysis (SNA), such as Degree Centrality, Closeness Centrality, and Betweenness Centrality. We also used average similarity, computational time, association rule with Apriori algorithm, and clustering performance evaluation as evaluation measures to compare method performance of recommender systems using Silhouette Coefficient, Calinski-Harabaz Index, and Davies–Bouldin Index.