Movie Dataset Research Articles

Data-driven portfolio management for motion pictures industry: A new data-driven optimization methodology using a large language model as the expert

Portfolio management is one of the unresponded problems of the Motion Pictures Industry (MPI). To design an optimal portfolio for an MPI distributor, it is essential to predict the box office of each project. Moreover, for an accurate box office prediction, it is critical to consider the effect of the celebrities involved in each MPI project, which was impossible with any precedent expert-based method. Additionally, the asymmetric characteristic of MPI data decreases the performance of any predictive algorithm. In this paper, firstly, the fame score of the celebrities is determined using a large language model. Then, to tackle the asymmetric character of MPI’s data, projects are classified. Furthermore, the box office prediction takes place for each class of projects. Finally, using a hybrid multi-attribute decision-making technique, the preferability of each project for the distributor is calculated, and benefiting from a bi-objective optimization model, the optimal portfolio is designed. To validate our approach, we conducted experiments using a dataset of movies released in the United States from 1980 to 2020 and employed the proposed approach to predict box office performance. Our results demonstrate that the proposed methodology significantly improves prediction accuracy and provides a robust framework for effective portfolio management.

Deep Spatio-Temporal Network for Low-SNR Cryo-EM Movie Frame Enhancement.

Cryo-EM in single particle analysis is known to have low SNR and requires to utilize several frames of the same particle sample to restore one high-quality image for visualizing that particle. However, the low SNR of cryo-EM movie and motion caused by beam striking make the task very challenging. Video enhancement algorithms in computer vision shed new light on tackling such tasks by utilizing deep neural networks. However, they are designed for natural images with high SNR. Meanwhile, the lack of ground truth in cryo-EM movie seems to be one major limiting factor of the progress. Hence, we present a synthetic cryo-EM movie generation pipeline, which can produce realistic diverse cryo-EM movie datasets with low-SNR movie frames and multiple ground truth values. Then we propose a deep spatio-temporal network (DST-Net) for cryo-EM movie frame enhancement trained on our synthetic data. Spatial and temporal features are first extracted from each frame. Spatio-temporal fusion and high-resolution re-constructor are designed to obtain the enhanced output. For evaluation, we train our model on seven synthetic cryo-EM movie datasets and infer on real cryo-EM data. The experimental results show that DST-Net can achieve better enhancement performance both quantitatively and qualitatively compared with others.

Content-based Recommender System Using Cosine Similarity

Abstract: In the quest for a more tailored cinematic experience, this paper presents a Movie Recommender System that harnesses the power of Cosine Similarity within a machine learning framework. The system’s cornerstone is its ability to discern nuanced user preferences and suggest films that resonate on a personal level. Employing Python, the research delineates a methodology that encompasses data collection, preprocessing, and feature extraction from a comprehensive dataset of movies. The crux of the system lies in its application of the cosine similarity algorithm, which calculates the affinity between movies and users based on shared characteristics such as genre, director, plot, title and cast. This approach is rigorously evaluated using metrics like precision, recall, and accuracy, ensuring the recommender’s reliability. The experimental design bifurcates the dataset into training and testing subsets, fortifying the system’s robustness. The paper’s findings illuminate the system’s efficacy in delivering precise and individualized recommendations, thereby augmenting the user’s movie selection process. It underscores the potential of the system to revolutionize content discovery and consumption in the entertainment domain. The conclusion encapsulates the project’s ambition to refine the recommender system further by integrating diverse machine learning algorithms and scaling its capabilities.

From Latent Dynamics to Meaningful Representations.

While representation learning has been central to the rise of machine learning and artificial intelligence, a key problem remains in making the learned representations meaningful. For this, the typical approach is to regularize the learned representation through prior probability distributions. However, such priors are usually unavailable or are ad hoc. To deal with this, recent efforts have shifted toward leveraging the insights from physical principles to guide the learning process. In this spirit, we propose a purely dynamics-constrained representation learning framework. Instead of relying on predefined probabilities, we restrict the latent representation to follow overdamped Langevin dynamics with a learnable transition density─a prior driven by statistical mechanics. We show that this is a more natural constraint for representation learning in stochastic dynamical systems, with the crucial ability to uniquely identify the ground truth representation. We validate our framework for different systems including a real-world fluorescent DNA movie data set. We show that our algorithm can uniquely identify orthogonal, isometric, and meaningful latent representations.

Sentiment Analysis for Movie Recommendation

Our research proposes a movie recommendation system integrating sentiment analysis with LSTM neural networks. By extracting sentiments from user reviews, LSTM captures nuanced preferences, enhancing recommendation accuracy. Leveraging real-world movie datasets, our approach outperforms existing methods, offering personalized recommendations aligned with user sentiments. Through this fusion of NLP and deep learning, we strive to streamline movie selection, providing users with a more tailored and satisfying experience. Keywords—Sentiment Analysis, Natural Language Processing,, Long Short-Term Memory, Recurrent Neural Network

Predicting user demographics based on interest analysis in movie dataset

Predicting user demographics based on interest analysis in movie dataset

Five Mars Years of Cloud Observations at Gale Crater: Opacities, Variability, and Ice Crystal Habits

We update the record of cloud opacity observations conducted by the Mars Science Laboratory (MSL) Curiosity rover to cover the first five Mars Years (MYs) of the mission (L s = 160° of MY 31 to L s = 160° of MY 36). Over the three MY period that we add to the previously analyzed two MY record, we achieve good diurnal coverage between 07:00 and 17:00 with nearly 1200 new observations. We derive a new scattering phase function for the clouds of the Aphelion Cloud Belt (ACB) using results from the Zenith and Suprahorizon movie data sets. Our phase function is generally smooth and featureless, which is consistent with the overall lack of atmospheric optical phenomena on Mars aside from a single instance of an observed halo. Applying our new phase function to the data, we find that there is very minimal variability in the ACB's opacity, either diurnally, intraseasonally, or interannually, noting that our observations are only sensitive to ice clouds and cannot detect any ice hazes that may be present over Gale. This contrasts with previous results, which observed a 57% difference in the opacity of morning and afternoon clouds in MY 33. The MY 33 results now appear to be an outlier, not replicated at any point during the MSL mission. We conclude that the higher morning opacities in MY 33 were a consequence of an incomplete understanding of the nature of the scattering phase function close to the Sun.

Dominance of AI and Machine Learning Techniques in Hybrid Movie Recommendation System Applying Text-to-number Conversion and Cosine Similarity Approaches

This research explored movie recommendation systems based on predicting top-rated and suitable movies for users. This research proposed a hybrid movie recommendation system that integrates both text-to-number conversion and cosine similarity approaches to predict the most top-rated and desired movies for the targeted users. The proposed movie recommendation employed the Alternating Least Squares (ALS) algorithm to reinforce the accuracy of movie recommendations. The performance analysis and evaluation were undertaken by employing the widely used "TMDB 5000 Movie Dataset" from the Kaggle dataset. Two experiments were conducted, categorizing the dataset into distinct modules, and the outcomes were contrasted with state-of-the-art models. The first experiment attained a Root Mean Squared Error (RMSE) of 0.97613, while the second experiment expanded predictions to 4800 movies, culminating in a substantially minimized RMSE of 0.8951, portraying a 97% accuracy enhancement. The findings underscore the essence of parameter selection in text-to-number conversion and cosine and the gap for other systems to maintain user preferences for comprehensive and precise data gathering. Overall, the proposed hybrid movie recommendation system demonstrated promising results in predicting top-rated movies and offering personalized and accurate recommendations to users.

Hybrid Recommender Systems based on Content Feature Relationship

Recommendation systems get ever-increasing importance due to their applications in both academia and industry. The most popular type of these systems, known as collaborative filtering algorithms, employ user-item interactions to perform the recommendation tasks. With growth of additional information sources other than the rating (or purchase) history of users on items, such as item descriptions and social media information, further extensions of these systems have been proposed, known as hybrid recommendation algorithms. Hybrid recommenders use both user-item interaction data and their contextual information. In this work, we propose new hybrid recommender algorithms by considering the relationship between content features. This relationship is embedded into the hybrid recommenders to improve their accuracy. We first introduce a novel method to extract the content feature relationship matrix, and then the collaborative filtering recommender is modified such that this relationship matrix can be effectively integrated within the algorithm. The proposed algorithm can better deal with the cold-start problem than the state-of-art algorithms. We also propose a novel content-based hybrid recommender system. Our experiments on a benchmark movie dataset show that the proposed approach significantly improves the accuracy of the system, while resulting in satisfactory performance in terms of novelty and diversity of the recommendation lists.

Research and improvement of movie recommendation based on a collaborative filtering algorithm

Among various recommendation algorithms, collaborative filtering stands out as a popular and effective technique that analyzes user behavior to suggest personalized items. The goal of studying recommendation algorithms is to enhance the exactness of recommendation outcomes and provide users with tailored suggestions. In this paper, the algorithm of collaborative filtering is divided into User-CF and Item-CF, and their algorithm principles and implementation steps are introduced. The similarity calculation of both methods is improved, and a comparison of their advantages and disadvantages is conducted. Experiments are conducted on the MovieLens-latest-small movie dataset to compare the performance of User-CF and Item-CF before and after their similarity calculation is improved. The results show that the similarity improvement of User-CF can substantially enhance the algorithms inclusiveness, while the similarity improvement of Item-CF does not have a considerable impact on the algorithms performance indicators. Finally, the comparison shows that Item-CF has better coverage and popularity, while User-CF has better precision and recall.

Towards evaluating robustness of violence detection in videos using cross-domain transferability

Recent studies have demonstrated the applicability of classification models based on deep learning for detecting human action. For this reason, automatic violence detection from videos has become a crying need to prevent the spreading of vulnerable content on digital platforms. In spite of the remarkable success of these neural networks, they are prone to fail against adversarial attacks and thus, highlighted the need for evaluating the robustness of these state-of-the-art violence detection classifiers. Here, we propose a transferable logit attack for binary misclassification of video data which can evade the system by our spatially perturbed synthesized adversarial samples. We utilize the adversarial falsification-based threat model to validate a non-sparse white-box attack setting which will generate cross-domain adversarial video samples by perturbing only spatial features without affecting the temporal features. We carry out extensive experiments on the validation set of two popular violence detection datasets: Hockey Fight Dataset, and Movie Dataset and verify that our proposed attack method has high attack success rate for these datasets against the state-of-the-art violence detection classifier. This work aims to make future violence detection models more resistant to adversarial examples.

Comparative Study of Various Classification and Regression Techniques on Movie Datasets Using R

The entertainment industry has been exponentially growing since its inception and is primarily well-received. Creating content, in this case, Movies has been the bread and butter of the industry and has proven extremely lucrative over the years. In this comparative study, we have picked out various Machine Learning models, viz. Classification Tree, Regression Tree, AdaBoost, SVM (Linear Kernel, Polynomial Kernel, Radial Kernel), XGBoost, Random Forest, Simple Bagging, and Naive Bayes. The Classification models are used to predict the rate of a certain movie winning the Oscar whereas the Regression model implementation estimates the average earning of a film considering the various attributes.

Adaptive genetic algorithm for user preference discovery in multi-criteria recommender systems

A Multi-Criteria Recommender System (MCRS) represents users’ preferences on several factors of products and utilizes these preferences while making product recommendations. In recent studies, MCRS has demonstrated the potential of applying Multi-Criteria Decision Making methods to make effective recommendations in several application domains. However, eliciting actual user preferences is still a major challenge in MCRS since we have many criteria for each product. Therefore, this paper proposes a three-phase adaptive genetic algorithm-based approach to discover user preferences in MCRS. Initially, we build a model by assigning weights to multi-criteria features and then learn the preferences on each criteria during similarity computation among users through a genetic algorithm. This allows us to know the actual preference of the user on each criteria and find other like-minded users for decision making. Finally, products are recommended after making predictions. The comparative results demonstrate that the proposed genetic algorithm based approach outperforms both multi-criteria and single criteria based recommender systems on the Yahoo! Movies dataset based on various evaluation measures.

Fine Grained Analysis of Intention for Social Media Reviews Using Distance Measure and Deep Learning Technique

Intent analysis and classification are performed to identify the expressions of intent in the given text. In this paper, the dataset is classified into emotion classifications by utilizing machine learning model SVM, Bipolar classification, Fine Grained Analysis, and Sarcasm detection, with Naïve Bayes and Random Forest techniques of deep learning, including Long Short-Term Memory to perform intention analysis on social media data. Then Fine-grained or Multi-Class Sentiment analysis is used for further classification of the five classes, viz. negative, strong negative, neutral, positive, and strong positive, which detects the sarcastic reviews in the movie dataset. The emotional intention behind the review comments is classified as happiness, rage, sadness, joy, anger, and disgust by using SVM. The reviews are analyzed and calculated based on their subjectivity and context level similarity using Related Relaxed Word Mover Distance (RRWMD) semantic similarity measure. With the advantage of the RRWMD algorithm, the reviews from the context containing deviated or irrelevant contents were removed before being applied to the classification algorithms, thereby reducing the execution time, which obtains a 3% improvement in accuracy. The disadvantage of the RRWMD algorithm is only one deep learning algorithm is compared. From the observed accuracy scores and classification reports, the LSTM has provided higher accuracy, despite the long execution time. The Naïve Bayes model has produced lower accuracy than the neural network model but was efficient, taking less time to fit and classify. The results from various experiments have proven that the semantic similarity measure provides more accurate results than the state-of-the-art model.

Research on multi-context aware recommendation methods based on tensor factorization

Compared to the traditional recommender systems, context-aware recommender systems are more in line with actual application contexts. However, the existing researches are mostly focused on single context-aware recommendation, such as time-aware recommendation or location-aware recommendation, and lack of in-depth research on multi-context-aware recommendation. Therefore, we proposed a recommendation method of high-order tensor factorization based on multi-context-aware. First, on the basis of analyzing the influence of context on users’ interest preferences, the sensitivity of users to multiple contexts was detected using statistical methods. For context-sensitive users, four-dimensional tensors and feature matrices used to solve data sparsity were constructed based on rating matrix and situational information. And then the stochastic gradient descent algorithm was used for iterative calculation to fill in missing data values and carry out parameter optimization. For context-insensitive users, we used matrix factorization to predict users’ interest preferences. Finally, we tested and validated our method on a multi-context-aware movie dataset, and the experimental results show that the proposed method could effectively reduce the prediction error and improve the recommendation quality.

Visual Analysis of Agricultural Workers using Explainable Artificial Intelligence (XAI) on Class Activation Map (CAM) with Characteristic Point Data Output from OpenCV-based Analysis

In this study, we use explainable artificial intelligence (XAI) based on class activation map (CAM) techniques. Specifically, we use Grad-CAM, Grad-CAM++, and ScoreCAM to analyze outdoor physical agricultural (agri-) worker image datasets. In previous studies, we developed body-sensing systems to analyze human dynamics with the aim of enhancing agri-techniques, training methodologies, and worker development. These include distant, visual data-based sensing systems that capture image and movie datasets related to agri-worker motion and posture. For this study, we first obtained the aforementioned image datasets for researcher review. Then, we developed and executed Python programs with Open-Source Computer Vision (OpenCV) libraries and PyTorch to run XAI-oriented systems based on CAM techniques and obtained heat map-pictures of the visual explanations. Besides, we implement optical flow-based image analyses using our Visual C++ programs with OpenCV libraries, automatically set and chase the characteristic points related to the video datasets. Next, we analyze the dataset features and compare experienced and inexperienced subject groups. We investigate the output’s features, accuracies, and robustness to be able to make recommendations for real agri-workers, managers, product-developers, and researchers. Our findings indicate that the visualized output datasets are especially useful and may support further development of applied methods for these groups.

Chatbot Using Deep Learning

In this paper we have proposed the working of Assistant conversational agent(Chatbot) using deep learning concepts with the utilization of tensorflow library. The LSTM is used overhere, so that the input taken with more than 30-40 words in a sentence canbe replied or answerd with more adequate conversation. The movie dataset used to train the model is taken from Cornell. The model isdesigned to perform a movie dialogue prediction conversation between the user and chatbot. The main aim is to increase the accuracy and estimation of the model. In the proposed model, we have developed a Seq2Seq AI Chatbot with attention mechanism using LSTM and libraries like tenserflow.

Hybrid Movie Recommendation System Using Machine Learning

This research suggests a hybrid movie recommendation system and optimization approach based on weighted classification and user collaborative filtering algorithm to address the issue that the single model of the standard recommendation system cannot adequately reflect user preferences. The top-N personalized movie recommendations are made by fusing the weighted classification model with the local recommendation model, which is trained based on user clustering, and the sparse linear model, which serves as the fundamental recommendation model. The scoring matrix is transformed into a low-dimensional, dense item category preference matrix based on item category preference, multiple cluster centers are obtained, the distance between each cluster center and the target user is calculated, and the target user is categorized into the closest cluster. Finally, a suggestion list is created using the collaborative filtering algorithm to forecast the scores for the target user's unrated items. The highdimensional rating matrix is transformed into a lowdimensional item category preference matrix, which further reduces the sparsity of the data. The items are then grouped based on item category preference. The recommendation algorithm suggested in this article addresses some of the limitations of a single algorithm model and enhances the suggestion effect, according to experiments using the MovieLens movie dataset.

Plot-aware transformer for recommender systems

<abstract> <p>Plot text is very valuable supporting information in movie recommendations. It has several characteristics: 1) It is rich in content. Each movie often has a document of more than 200 words to describe it, which can give the movie a rich semantic meaning. 2) Objectivity. Plot texts are different from review information. A movie may have thousands of reviews with mixed and conflicting opinions. However, a film has only one plot text, which is fair in tone and does not take a position. Despite its appealing properties and potential for accurate movie portrayal, the lack of a building block for effectively mining plot semantics has led to the marginalization of plot text in the design of movie recommendation algorithms. Therefore, in this paper, we explore the application of the Transformer, currently the best natural language processing module, to learning movie plot texts to help achieve more accurate rating prediction. We propose the "Plot-Aware Transformer" model (PAT) to model the process of "user-movie" rating interaction. We test the PAT model on several movie datasets and demonstrated that the model is competitive. In all tasks, PAT achieves state-of-the-art performance compared to baseline experiments.</p> </abstract>

Correlation Analysis between Ethnic Diversity and Success Rate on a Massive Repository of Movies Data Set and the Board of Directors of Fortune 500 in Terms of Net Sales and Gross Profit

Correlation Analysis between Ethnic Diversity and Success Rate on a Massive Repository of Movies Data Set and the Board of Directors of Fortune 500 in Terms of Net Sales and Gross Profit