Internet Movie Database Research Articles

Exploring the Impact of Word2Vec Embeddings Across Neural Network Architectures for Sentiment Analysis

Abstract. Sentiment analysis is crucial for understanding public opinion, gauging customer satisfaction, and making informed business decisions based on the emotional tone of textual data. This study investigates the performance of different Word2Vec-based embedding strategies static, non-static, and multichannel for sentiment analysis across various neural network architectures, including Convolution Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRUs). Despite the rise of advanced contextual embedding methods such as Bidirectional Encoder Representations from Transformers (BERT), Word to Vector (Word2Vec) retains its importance due to its simplicity and lower computational demands, making it ideal for use in settings with limited resources. The goal is to evaluate the impact of fine-tuning Word2Vec embeddings on the accuracy of sentiment classification. Using the Internet Movie Database (IMDb), this work finds that multichannel embeddings, which combine static and non-static representations, provide the best performance across most architectures, while static embeddings continue to deliver strong results in specific sequential models. These findings highlight the balance between efficiency and accuracy in traditional word embeddings, particularly when advanced models are not feasible.

The Fictional Archetypes of AI: For a Qualitative-Quantitative Analysis of Representations in Films

MOS research on films has tended to focus on individual cases or series. In this article, we are proposing an approach that mobilizes background analysis, computational text analysis, and hermeneutics in order to provide a systematic, critically inclined analysis of a large corpus. We illustrate this approach by exploring the political and symbolical representations of artificial intelligence (AI) in the film industry. Using the Internet Movie Database, we identified all the films dealing with AI (113 in total), compiled their synopses, and recorded 11 characteristics for each. Highlighting the spatial, temporal, and gendered polarization of films depicting AI, our article proposes four representations of AI and critically reflects upon the role of these representations and their influence in shaping societal perceptions of AI. Our article makes two main contributions to the literature. First, it demonstrates the potential of combining quantitative-based, lexical forms of analysis with hermeneutic interpretations in the study of cultural representations. Second, it develops a nuanced, in-depth, and critical analysis of the symbolical and political representations of AI in cinematic productions, thus enhancing our understanding of this industry.

Natural Language Processing and Machine Learning-Based Solution of Cold Start Problem Using Collaborative Filtering Approach

In today’s digital era, the abundance of online services presents users with a daunting array of choices, spanning from streaming platforms to e-commerce websites, leading to decision fatigue. Recommendation algorithms play a pivotal role in aiding users in navigating this plethora of options, among which collaborative filtering (CF) stands out as a prevalent technique. However, CF encounters several challenges, including scalability issues, privacy implications, and the well-known cold start problem. This study endeavors to mitigate the cold start problem by harnessing the capabilities of natural language processing (NLP) applied to user-generated reviews. A unique methodology is introduced, integrating both supervised and unsupervised NLP approaches facilitated by sci-kit learn, utilizing benchmark datasets across diverse domains. This study offers scientific contributions through its novel approach, ensuring rigor, precision, scalability, and real-world relevance. It tackles the cold start problem in recommendation systems by combining natural language processing (NLP) with machine learning and collaborative filtering techniques, addressing data sparsity effectively. This study emphasizes reproducibility and accuracy while proposing an advanced solution that improves personalization in recommendation models. The proposed NLP-based strategy enhances the quality of user-generated content, consequently refining the accuracy of Collaborative Filtering-Based Recommender Systems (CFBRSs). The authors conducted experiments to test the performance of the proposed approach on benchmark datasets like MovieLens, Jester, Book-Crossing, Last.fm, Amazon Product Reviews, Yelp, Netflix Prize, Goodreads, IMDb (Internet movie Database) Data, CiteULike, Epinions, and Etsy to measure global accuracy, global loss, F-1 Score, and AUC (area under curve) values. Assessment through various techniques such as random forest, Naïve Bayes, and Logistic Regression on heterogeneous benchmark datasets indicates that random forest is the most effective method, achieving an accuracy rate exceeding 90%. Further, the proposed approach received a global accuracy above 95%, a global loss of 1.50%, an F-1 Score of 0.78, and an AUC value of 92%. Furthermore, the experiments conducted on distributed and global differential privacy (GDP) further optimize the system’s efficacy.

The Kinomatics Australian Film Production Dataset: A Curated Dataset Describing Australian Feature Film Titles and Personnel 1975–2022

Abstract This article presents a novel, extensive, and thoroughly documented dataset describing Australian feature films and the personnel filling ten key production roles on those films. The dataset is curated from public information in multiple sources and draws on further supplemental resources to verify, validate and consolidate this information. In total, the data describes 22,720 roles filled by 9,397 distinct people across 1,877 films, covering an important 47-year period in the Australian film industry. The authors outline how the dataset solves several problems for scholars interested in data that provides a historical record of the collaborative filmmaking process. In particular, to address concerns about known coverage problems with popular sources such as the Internet Movie Database, this dataset has undergone extensive manual checking to ensure that it is reliable as a source of information on a national film industry. Moreover, the authors have carefully and manually linked each person appearing in the dataset, which allows the dataset to provide a rich source of information for exploring the relationality of filmmaking collaborations. The inclusion of ten key filmmaking roles further expands the utility of the dataset beyond existing datasets which tend to focus on actors and/or directors, writers and producers.

Content Specific Keyboard Layout Design for Smart Tv Applications

This research aims to propose a genetic algorithm based methodology to design optimum keyboard layout for video streaming applications designed for smart TVs. Users need to use the arrow buttons on their remote controls to type the title of the movie or the TV show they are searching for. We downloaded approximately 9 million movie and TV show titles from the Internet Movie Database (IMDB) website. After data preprocessing, we calculated the frequency of letter sequences in these titles and used genetic algorithms to determine the optimum keyboard layout that would minimize the total number of clicks required to type the title using arrow buttons on a remote control. The proposed keyboard layout is tested using the movie titles in IMBD Top 100 list and compared with standard QWERTY keyboard and three other keyboards in alphabetical order. It was confirmed that the proposed keyboard layout required fewer number of clicks than other keyboard layouts in 83 titles and tied with one of the other keyboards in 4 titles.

An acronym for Internet Movie Database is an online database of information related to films, television, series

Abstract: Movie recommender systems are meant to give suggestions to the users based on the features they love the most. A highly performing movie recommendation will suggest movies that match the similarities with the highest degree of performance. This study conducts a systematic literature review on movie recommender systems. It highlights the filtering criteria in the recommender systems, algorithms implemented in movie recommender systems, the performance measurement criteria, the challenges in implementation, and recommendations for future research. Some of the most popular machine learning algorithms used in movie recommender systems such as K-means clustering, principal component analysis, and self-organizing maps with principal component analysis are discussed in detail. Special emphasis is given to research works performed using metaheuristic-based recommendation systems. The research aims to bring to light the advances made in developing the movie recommender systems, and what needs to be performed to reduce the current challenges in implementing the feasible solutions. The article will be helpful to researchers in the broad area of recommender systems as well as practicing data scientists involved in the implementation of such systems. Index-terms : movie recommender, filtering techniques, performance metrics, K-means, metaheuristics

A statistical approach to Hollywood remake and sequel metadata

Abstract Hollywood film remakes, as old as the cinema itself, have attracted much professional, critical, and academic attention. They have been viewed by art critics as products of cultural derivativity and imperialism and commended by financial experts as low-risk business investments, closely linked to other forms of brand extension, such as sequels and bestseller adaptations. In this article, we adopt a film-historical quantitative approach to Hollywood film remakes by analysing metadata obtained from the Internet Movie Database (IMDb) and verified against reliable print and web sources. We analyse 986 Hollywood remakes produced between 1915 and 2020 in terms of raw and relative frequencies of annual releases, genre (in)stability, and patterns of transnational reproduction. We contrast our findings with those outlined by Henderson (2014a) in his statistical survey of Hollywood sequels, series films, prequels, and spin-offs, presented in his monograph The Hollywood Sequel: History and Form, 1911–2010. Having completed his list with recent sequential productions released between 2011 and 2020, we investigate the potential parallels between Hollywood remaking and sequelization practices. Our findings demonstrate historical discrepancies in various ‘content recycling’ trends, which help better characterize the cultural and commercial significance of remakes and serial forms in the American film industry.

Redefining Orientalism Through “Squid Game”: Sentiment Analysis And Word Cloud R Studio

This article aims to redefine Edward Said's definition of orientalism in the era of contemporary communication and information technology through the comments column for the film Squid Game on the IMDB (internet movie database) website. This paper argues that the Orientalist attitude of a dominant English-speaking country such as the United States emerged as a consequence of its white superior hegemony. In the midst of this orientalist attitude, today's communication and information technology has become a discursive channel for the world community to conduct ongoing discussions on films by Asians. By using the text in the comment column for the film Squid Game on IMDB.com as a case example, this article provides a discussion regarding the need to rethink the conceptual definition of orientalism today. This paper uses a digital research methodology with analysis tools using R Studio with two types of analysis, namely word cloud and sentiment analysis. By utilizing the programming language functions available in R Studio, this paper mines text from the IMDB.com comments column for the film Squid Game. This article contains results obtained from digital research methods, namely the Squid Game comments column focuses on characters, plot, acting and story. Meanwhile, sentiment analysis shows the dominance of positive sentiment and some negative sentiment. Therefore, this article argues that the battle between negative and positive sentiments in the Squid Game comments column is a means of resetting the negative stigma towards Asian films and eroding the orientalist attitudes that the West oppresses towards "the East."

Self-supervised text de-stylization based on BERT

Recent advancements in Natural Language Processing (NLP) have ushered in a new era of textual style transfer (TST), a domain aimed at altering textual attributes such as tone and sentiment while preserving the content's essence. This study introduces a creative framework that employs a dual-component architecture consisting of a classifier and a generator to achieve text de-stylization, particularly sentiment neutralization. The classifier, built upon the Bidirectional Encoder Representations from Transformers (BERT) model, serves as a dynamic loss function guiding the generator, constructed on a Transformer-based encoder-decoder framework, to produce sentiment-neutral text. Our method leverages a self-supervised mechanism, enabling the generation of target text without reliance on parallel corpora, thereby addressing the limitations of existing TST methodologies. We preprocessed datasets from Stanford Sentiment Treebank-5 (SST-5) and Internet Movie Database (IMDb) movie reviews and employed them for training the classifier and generator, respectively. Preliminary results demonstrate the model's proficiency in preserving semantic integrity while effectively neutralizing sentiment. Future work envisions expanding this framework to enable text stylization across a spectrum of discursive contexts, enhanced by deep learning architectures and an iterative feedback mechanism for user-driven refinement.

They Have Never Changed: Accountants in Movies

The purpose of this study is to examine how accountants are portrayed in recent box office films. The samples for this study were movies registered in the Internet Movie Database and Film Indonesia. The study focuses on the accountant who appears in movies as a main character, side character, and/or cameo. Movies with accountant as the character and winning at least one award were chosen in this study. The semiotic analysis of movie data involved three steps: viewing the entire film, focusing on the accountants’ character scene in accordance with the description criteria, and interpreting the characters denotatively, connotatively, and mythically. The findings demonstrate that the stereotype of accountants shown in movies is consistent with societal preconceptions, such as being a man's occupation, having a bean counter, being introverted, and committing money theft. However, in some movies, accountants are portrayed positively. This negative depiction of accountants may cause students to be reluctant to choose accountants as their career choice. Thus, public accounting firms will encounter difficulties in recruiting and sustaining their businesses. Framed with the social representation theory, this study contributes to the accounting literature by focusing on the depiction of the accountant's character shown in the film by using semiotic analysis to investigate the depiction of accountants in films released since 2000.

Heterogeneous text graph for comprehensive multilingual sentiment analysis: capturing short- and long-distance semantics.

Multilingual sentiment analysis (MSA) involves the task of comprehending people's opinions, sentiments, and emotions in multilingual written texts. This task has garnered considerable attention due to its importance in extracting insights for decision-making across diverse fields such as marketing, finance, and politics. Several studies have explored MSA using deep learning methods. Nonetheless, a majority of these studies depend on sequential-based approaches, which focus on capturing short-distance semantics within adjacent word sequences, but they overlook long-distance semantics, which can provide more profound insights for analysis. In this work, we propose an approach for multilingual sentiment analysis, namely MSA-GCN, leveraging a graph convolutional network to effectively capture both short- and long-distance semantics. MSA-GCN involves the comprehensive modeling of the multilingual sentiment analysis corpus through a unified heterogeneous text graph. Subsequently, a slightly deep graph convolutional network is employed to acquire predictive representations for all nodes by encouraging the transfer learning across languages. Extensive experiments are carried out on various language combinations using different benchmark datasets to assess the efficiency of the proposed approach. These datasets include Multilingual Amazon Reviews Corpus (MARC), Internet Movie Database (IMDB), Allociné, and Muchocine. The achieved results reveal that MSA-GCN significantly outperformed all baseline models in almost all datasets with a p-value < 0.05 based on student t-test. In addition, such approach shows prominent results in a variety of language combinations, revealing the robustness of the approach against language variation.

Analysis of Internet Movie Database with Global Vectors for Word Representation

Sentiment analysis (SA) involves utilizing natural language processing (NLP) methods to identify the sentiment conveyed by a given text. This study is grounded on the dataset sourced from the internet movie database (IMDB), encompassing evaluations of films and their corresponding positive or negative classifications. Our research experiment aims to ascertain the model with the highest accuracy and generality. Our research utilizes diverse classifiers, comprising unsupervised learning approaches such as Valence Aware Dictionary and sEntiment Reasoner (VADER) and Text Blob, alongside Supervised Learning methods like Naïve Bayes, which encompasses both the Bernoulli NB and Multinomial NB. Several methodologies have been utilized, including the Count Vectorizer, and the Term Frequency-Inverse Document Frequency model (TFIDF) Vectorizer. Subsequently, word embedding and bidirectional LSTM are executed, utilizing various embeddings such as the Long Short-Term Memory (LSTM) base model. Finally, GloVe embeddings achieve the best performance with an accuracy of 90.64% and a sensitivity of 91.07%.

Online images amplify gender bias

Each year, people spend less time reading and more time viewing images1, which are proliferating online2–4. Images from platforms such as Google and Wikipedia are downloaded by millions every day2,5,6, and millions more are interacting through social media, such as Instagram and TikTok, that primarily consist of exchanging visual content. In parallel, news agencies and digital advertisers are increasingly capturing attention online through the use of images7,8, which people process more quickly, implicitly and memorably than text9–12. Here we show that the rise of images online significantly exacerbates gender bias, both in its statistical prevalence and its psychological impact. We examine the gender associations of 3,495 social categories (such as ‘nurse’ or ‘banker’) in more than one million images from Google, Wikipedia and Internet Movie Database (IMDb), and in billions of words from these platforms. We find that gender bias is consistently more prevalent in images than text for both female- and male-typed categories. We also show that the documented underrepresentation of women online13–18 is substantially worse in images than in text, public opinion and US census data. Finally, we conducted a nationally representative, preregistered experiment that shows that googling for images rather than textual descriptions of occupations amplifies gender bias in participants’ beliefs. Addressing the societal effect of this large-scale shift towards visual communication will be essential for developing a fair and inclusive future for the internet.

A Predictive Analysis of IMDb Movie Reviews Using LSTM and ANN Models

The Machine Learning domain has made a major process with the progression of state-of-the-art technologies. Since current algorithms often don’t provide palatable learning performance, it is necessary to continually upgrade them. This paper has illustrated the comparison of the Long Short-Term Memory (LSTM) model and the Artificial Neural Networks (ANN) model in the prediction of the Internet Movie Database (IMDb) website. These evaluations were then related to sentiment assessment approaches to evaluate their predicted accuracy and performances. The results demonstrate that the ANN model outperforms the LSTM model with a high accuracy rate in terms of the prediction accuracy and loss indicators for the IMDb movie review’s sentiment analysis task in terms of the prediction accuracy and loss indicators for the IMDb movie review’s sentiment analysis task. The accuracy of prediction on the test dataset of the ANN model is 83.5 % and the LSTM model is 83.5%. Therefore, it can be concluded that the standard artificial neural network model that was utilized is an appropriate technique for sentiment assessment tasks in IMDb rating text data.

Communities of Style: Artistic Transformation and Social Cohesion in Hollywood, 1930 to 1999

How do social and stylistic relations in cultural fields coevolve under changing contextual conditions? Artistic communities cohere through collaborations and shared stylistic orientations among artists, but little is known about the structure and interplay of these relational processes. The authors contribute to previous studies by conducting a large-scale investigation of social and stylistic networks among Hollywood filmmakers. In particular, the authors examine how the interplay between artists’ collaborations and shared references changed throughout Hollywood’s history. Using data from the Internet Movie Database and applying relational hyperevent models, the authors analyze the coevolution of collaboration and reference networks among 15,553 Hollywood film professionals who participated in 6,800 films between 1930 and 1999. The authors complement prior sociological efforts through a longitudinal perspective on the structure of social and stylistic networks across three meaningful historical periods: before, during, and after Hollywood’s artistic transformation in the 1960s. The findings show that filmmakers are more likely to collaborate if they previously used the same references, but they are less likely to adopt the references of their previous collaborators. In addition, the results highlight that the structure of relational processes in cultural fields varies over time as the contextual conditions for tie formation change.

Abstract 13871: Portrayal of Acute Myocardial Infarction in Popular Film

Introduction: The representation of cardiovascular disease (CVD) in popular media plays a pivotal role in shaping public conceptions about CV health. CVD is the leading cause of death among women and disproportionately affects racial/ethnic minority populations in the United States, yet recent national surveys indicate a significant decline in public awareness. Our study sought to investigate the portrayal of acute myocardial infarction (AMI) in popular film. Hypothesis: Portrayal of AMI in film will predominantly show white men exhibiting symptoms of chest pain. Women, racial/ethnic minority populations, and subtle symptoms of AMI will be underrepresented. Aims: To examine 100 full length feature film scenes depicting AMI and evaluate the representation of gender, race/ethnicity, and symptoms. Methods: The 100 most popular films with scenes depicting AMI were identified using the Internet Movie Database (IMDb). Scenes and AMI symptoms were analyzed by cardiologists/cardiology fellows. Gender and race/ethnicity were acquired via movie plots/scripts or via actor self-identification if the former was unavailable. Results: Of the 100 scenes analyzed, 10% depicted women. The representation of people of color was only 6% in contrast to the 94% of scenes featuring non-Hispanic whites. Of the 10 women portrayed, 1 was non-white. The distribution of gender and race/ethnicity for all scenes is shown in Figure 1. The most prevalent presenting symptom observed in 65% of scenes was chest pain accompanied by loss of consciousness. Conclusions: Popular film depictions of AMI appear to be under representative of women and racial/ethnic minority populations. This may be a contributing factor to the inaccurate public perception that CVD does not affect these populations. Film depictions of AMI, which predominantly portray dramatic symptoms of chest pain and loss of consciousness may also perpetuate false beliefs on typical (or even atypical) symptoms of AMI.

Analysis of the Internet Reviews of The Wandering Earth 2 in China and America Based on Hofstede's Cultural Dimensions

Films are carriers of a countrys culture, thus building a powerful film country is to build a strong cultural country. In this context, ensuring the smooth sailing of Chinese films is of great significance. Taking The Wandering Earth 2 as an example, this research builds a cultural dimensional model of films communication effects under Hofstedes cultural dimensions. Based on a self-built corpus of reviews which contains 200 most heated comments from the Internet Movie Database (IMDb) and Douban, the research applies an original codebook consisting of 12 two grade indicators to rationalize audience cultural sensing. It is found that the sensing of Chinese viewers on the four dimensions averagely higher than the ones of American viewers, while the long-term orientation provides a possible common ground in both sides. The differences in the audiences internet reviews of The Wandering Earth 2 give a clue to the needs of soft landing, hard core and human touch, which Chinese films should well adopt as the key capabilities in cross-cultural diffusion.

Research on improving the generalization ability of NLP categorization models: A comparison of Mixup and generative adversarial networks

The application of deep neural networks in tasks related to natural language processing has grown in recent years. However, training deep learning models often requires a large amount of data to produce accurate and generalizable results. When the data are insufficient, categorization models may suffer from overfitting or poor performance. This paper compares two methods for enhancing the generalization ability of natural language processing categorization models when data are insufficient: Mixup and Generative Adversarial Networks (GANs). This paper uses the Internet Movie Database (IMDB) dataset for a binary classification task, Mixup method, and Relational Generative Adversarial Networks (RelGAN) model to generate new data, respectively, and compares them with the original dataset. Experimental results indicate that Mixup method can reduce overfitting risk effectively and enhance the models robustness, while the GAN model does not show obvious advantages. This paper supports the idea that using noise-adding operations to enhance the dataset is feasible in the case of small samples rather than using generative models.

Manifold-based sparse representation for opinion mining

What the consumer thinks about an organization's products, services, and events is a crucial performance indicator for businesses. The brief opinion pieces were quickly published on websites and social media platforms and have been analyzed by machine learning methods. The classical text feature representation methods suffer from high dimensionality, sparsity, noisy, irrelevant and redundant information. This paper focuses on how to enhance feature representation for opinion mining. Some nonlinear feature selection methods based on manifold assumption have been exploited to resolve these problems. The inherent manifold configuration was commonly ascertained through a nearest neighbor graph, whereby the neighbors in the current techniques may exhibit diverse polarities. To alleviate this burden, it is proposed to exploit both manifold assumption and sparse property as prior knowledge for opinion representation to learn intrinsic structure from data. First, the graph representation of user reviews based on the mentioned prior knowledge is learned. Then, the spectral properties of the learned graph are exploited to present data in a new feature space. The proposed algorithm is applied to four various common input features on two benchmark datasets, the Internet Movie Database (IMDB) and the Amazon review dataset. Our experiments reveal that the proposed algorithm yields considerable enhancements in terms of F-measure, accuracy, and other standard performance measures compared to the combination of state-of-the-art features with various classifiers. The highest classification accuracies of 99.15 and 91.97 are obtained in the proposed method on IMDB and Amazon using a linear SVM classifier, respectively. The impact of the parameters of the proposed algorithm is also investigated in this paper. The incorporation of a sparse manifold-based representation has led to noteworthy advancements beyond the baseline, and this success serves to validate the underlying assumptions.

Neuromorphic Sentiment Analysis Using Spiking Neural Networks.

Over the past decade, the artificial neural networks domain has seen a considerable embracement of deep neural networks among many applications. However, deep neural networks are typically computationally complex and consume high power, hindering their applicability for resource-constrained applications, such as self-driving vehicles, drones, and robotics. Spiking neural networks, often employed to bridge the gap between machine learning and neuroscience fields, are considered a promising solution for resource-constrained applications. Since deploying spiking neural networks on traditional von-Newman architectures requires significant processing time and high power, typically, neuromorphic hardware is created to execute spiking neural networks. The objective of neuromorphic devices is to mimic the distinctive functionalities of the human brain in terms of energy efficiency, computational power, and robust learning. Furthermore, natural language processing, a machine learning technique, has been widely utilized to aid machines in comprehending human language. However, natural language processing techniques cannot also be deployed efficiently on traditional computing platforms. In this research work, we strive to enhance the natural language processing traits/abilities by harnessing and integrating the SNNs traits, as well as deploying the integrated solution on neuromorphic hardware, efficiently and effectively. To facilitate this endeavor, we propose a novel, unique, and efficient sentiment analysis model created using a large-scale SNN model on SpiNNaker neuromorphic hardware that responds to user inputs. SpiNNaker neuromorphic hardware typically can simulate large spiking neural networks in real time and consumes low power. We initially create an artificial neural networks model, and then train the model using an Internet Movie Database (IMDB) dataset. Next, the pre-trained artificial neural networks model is converted into our proposed spiking neural networks model, called a spiking sentiment analysis (SSA) model. Our SSA model using SpiNNaker, called SSA-SpiNNaker, is created in such a way to respond to user inputs with a positive or negative response. Our proposed SSA-SpiNNaker model achieves 100% accuracy and only consumes 3970 Joules of energy, while processing around 10,000 words and predicting a positive/negative review. Our experimental results and analysis demonstrate that by leveraging the parallel and distributed capabilities of SpiNNaker, our proposed SSA-SpiNNaker model achieves better performance compared to artificial neural networks models. Our investigation into existing works revealed that no similar models exist in the published literature, demonstrating the uniqueness of our proposed model. Our proposed work would offer a synergy between SNNs and NLP within the neuromorphic computing domain, in order to address many challenges in this domain, including computational complexity and power consumption. Our proposed model would not only enhance the capabilities of sentiment analysis but also contribute to the advancement of brain-inspired computing. Our proposed model could be utilized in other resource-constrained and low-power applications, such as robotics, autonomous, and smart systems.