Online Movie Reviews Research Articles

How are PreLaunch online movie reviews related to box office revenues?

How are PreLaunch online movie reviews related to box office revenues?

Scalable deep learning framework for sentiment analysis prediction for online movie reviews

Sentiment analysis has broad use in diverse real-world contexts, particularly in the online movie industry and other e-commerce platforms. The main objective of our work is to examine the word information order and analyze the content of texts by exploring the hidden meanings of words in online movie text reviews. This study presents an enhanced method of representing text and computationally feasible deep learning models, namely the PEW-MCAB model. The methodology categorizes sentiments by considering the full written text as a unified piece. The feature vector representation is processed using an enhanced text representation called Positional embedding and pretrained Glove Embedding Vector (PEW). The learning of these features is achieved by inculcating a multichannel convolutional neural network (MCNN), which is subsequently integrated into an Attention-based Bidirectional Long Short-Term Memory (AB) model. This experiment examines the positive and negative of online movie textual reviews. Four datasets were used to evaluate the model. When tested on the IMDB, MR (2002), MRC (2004), and MR (2005) datasets, the (PEW-MCAB) algorithm attained accuracy rates of 90.3%, 84.1%, 85.9%, and 87.1%, respectively, in the experimental setting. When implemented in practical settings, the proposed structure shows a great deal of promise for efficacy and competitiveness.

A new branch of fake review detection research -- A review of fake review detection in the Chinese film industry in the post-epidemic era

In the post-pandemic era, Chinese moviegoers increasingly rely on online movie reviews, but fake reviews by spreaders can mislead moviegoers to make wrong decisions. Fake review detection has been developed to a certain extent in China. However, there is a lack of application research in the film industry. This paper summarizes some of the more advanced fake review detection methods in China in the post-epidemic era from the perspectives of review text detection and reviewer detection, introduces their indicators, feature selection methods, and training methods, and further discusses the specific steps of these methods in the detection of fake movie reviews combined with the characteristics of fake movie reviews. The research of this paper can bring guidance for the future detection of fake movie reviews, and provide a decision-making basis for consumers and investors.

Deep learning based bi-polar sentiment classification of movie reviews in Hindi

With evolving technology, Hindi web content is growing considerably and catching popularity as the larger audience feels more connected and heard using their native language. A volcanic growth in online movie reviews (MRs) in Hindi has been observed lately; manually analyzing them is impossible. Hence, the research problem of automatic organization and classification of Hindi reviews is apparent as this can help viewers decide whether a movie is worth watching or not. This work focuses on developing a deep learning-based system for bi-polar sentiment classification of MRs for resource deficient language – Hindi. To this end, a primary Hindi movie review (MR) corpus is made and manually annotated with binary polarity class labels - positive or negative. The corpus is preprocessed using the preprocessing steps, and Random Word Embeddings (WEs) are utilized for feature extraction. This paper proposes an ensemble CNN_BiGRU, which is an integration of 1D CNN with BiGRU for the bipolar classification of Hindi MRs. To prove our ensemble’s efficacy; other widely used mainstream deep learning models (DLMs) such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) based models – Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), are also applied and compared with proposed ensemble using average classification accuracy. Empirical results show the effectiveness of the proposed ensemble in achieving a reasonably good average accuracy of 89.366%. The results indicate that proposed CNN_BiGRU compares favorably to the state-of-the-art DLMs applied and hence gives an effective solution for sentence-level bi-polar classification of MRs in a resource deficient scenario.

The Effectiveness of Ideological Communication in Mainstream Films Based on Semantic Networks --Taking the Chinese and American Movie Reviews of Top Gun: Maverick as an Example

The co-occurrence networks are used as a tool for examining and interpreting discourse analysis to reveal the attitudes and perceptions implicit in film reviews. Based on the self-constructed corpus of online movie reviews in China and the United States, this research generates co-occurrence word-sense networks and summarizes three frameworks: sequel narrative, heroic narrative, and military narrative, and further reveals and explains the ideologies and linguistic features revealed in the different discourse frames. At the macro level, the Chinese and American audiences evaluation of the film shows different results of medium and medium-high. At the micro level, corresponding to the three frames, Chinese and American audiences construct images of commercial sentiment films and dramatic action films, national propaganda films and Hollywood hero films, U.S. Air Force propaganda films and U.S. Army recruitment advertising films; under the hero narrative frame, individual heroism and collectivism are realized side by side in the audiences discourse; under the military narrative frame, the political identity of transnational narratives is not realized in Chinese audiences.

Research on Movie Reviews based on Network Communication

This article analyzes the popularity and audience scope of movie reviews, and reveals the important position of movie reviews in online communication. Conduct an in-depth analysis of the diverse forms of film reviews, including written reviews, film review videos, social media discussions, etc., and explore their impact on review content and audience engagement. Study users' participation levels, interaction forms and opinion exchanges in online movie reviews, and reveal users' roles and behavioral characteristics in reviews. It also explores the impact of fake reviews and trolls on the authenticity and credibility of reviews, as well as the impact of information overload and screening difficulties on audience selection and decision-making. Finally, an information review mechanism and personalized recommendation technology to strengthen online movie reviews are proposed to help users better filter and obtain movie review information that meets their preferences.

Comic techniques as the means of transmitting negative evaluation in the English-language online movie reviews

Comic techniques as the means of transmitting negative evaluation in the English-language online movie reviews

Do cultural orientations moderate the effect of online review features on review helpfulness? A case study of online movie reviews

The perceived helpfulness of online product reviews plays a critical role in consumers’ decisions in e-commerce. In this context, based on the literature on information processing and cultural effects, this study explored the role of review features in the perceived helpfulness of online movie reviews. A cross-cultural investigation (i.e., China cf. the United States (US)) was employed to identify high-vs. low-context cultural orientation and uncertain avoidance orientation as moderators. The results reveal that review length, timeliness, title sentiment, and emotional expressions are significant predictors of helpfulness for consumer reviews in China and the US. In addition, cultural differences between the two countries, that is, high-vs. low-context culture and uncertainty avoidance, moderated the relationships between review length, timeliness, title sentiments, and review helpfulness.

Doc2Vec-based Approach for Extracting Diverse Evaluation Expressions from Online Review Data

This paper proposes a method for extracting diverse expressions from online movie review texts for a given keyword query. When people watch a movie that makes them cry, they generally do not say ``I cried.'' Instead, they use such euphemistic language as ``I needed a handkerchief'' or ``My makeup was running.''To enable information retrieval based on audience reactions such as ``movies that make me cry'' using review texts, various paraphrased expressions must be collected for arbitrary queries. Our proposed method extracts such expressions from review datasets by applying two extensions to Doc2Vec: 1) it changes the granularity of the training sentences to mitigate a lack of context, and 2) it applies query expansion for similarity calculation in advance.We conducted a large-scale crowdsourcing experiment with 1.29 million actual sentences taken from Yahoo! Movies, Japan. The experimental result revealed that changing the training data granularity and adding the query expansion effectively collect more diverse expressions that have a meaning similar to the given query.

Towards Reliable Baselines for Document-Level Sentiment Analysis in the Czech and Slovak Languages

This article helps establish reliable baselines for document-level sentiment analysis in highly inflected languages like Czech and Slovak. We revisit an earlier study representing the first comprehensive formulation of such baselines in Czech and show that some of its reported results need to be significantly revised. More specifically, we show that its online product review dataset contained more than 18% of non-trivial duplicates, which incorrectly inflated its macro F1-measure results by more than 19 percentage points. We also establish that part-of-speech-related features have no damaging effect on machine learning algorithms (contrary to the claim made in the study) and rehabilitate the Chi-squared metric for feature selection as being on par with the best performing metrics such as Information Gain. We demonstrate that in feature selection experiments with Information Gain and Chi-squared metrics, the top 10% of ranked unigram and bigram features suffice for the best results regarding online product and movie reviews, while the top 5% of ranked unigram and bigram features are optimal for the Facebook dataset. Finally, we reiterate an important but often ignored warning by George Forman and Martin Scholz that different possible ways of averaging the F1-measure in cross-validation studies of highly unbalanced datasets can lead to results differing by more than 10 percentage points. This can invalidate the comparisons of F1-measure results across different studies if incompatible ways of averaging F1 are used.

Exploration of Social Attitudes and Summarization of Film Reviews

The goal of this study was to identify the specific characteristics of internet reviews that made them useful. An online movie review site, Rotten Tomatoes, was used to gather online movie reviews. The online impact factor review methodology developed in this research makes use of data mining methods. A study found that article quality influences users' views of the effectiveness of interventions. When a reviewer has a happy mood, a strong emotional predisposition, and a high degree of review reliability, their material is more effective. Negative emotions, on the other hand, are less beneficial and weaker. Emotionally charged assessments are shown to have a greater number of reviews and tend to be more effective. The results of this study, which looked at how people evaluate online reviews, could help come up with new ways to predict economic success.

Effects of Sentiment Analysis on Feedback Loops between Different Types of Movies

This research was conducted with the intention of determining the specific qualities of internet reviews that contributed to their usefulness. The collected online movie reviews were found on the website Rotten Tomatoes, which is dedicated to film criticism. The methodology for conducting online reviews of impact factors that was developed as a result of this research makes use of data mining techniques. According to the findings of one study, users' perceptions of the efficacy of interventions are influenced by the quality of the articles. The effectiveness of a reviewer's contributions is increased when they are in a good mood, have a strong emotional predisposition, and a high degree of review reliability. On the other hand, negative emotions are both less beneficial and weaker than their positive counterparts. It has been demonstrated that emotionally charged evaluations receive a greater number of reviews and have a tendency to be more effective. The findings of this research, which investigated the manner in which individuals evaluate online reviews, could assist in the development of novel methods that are capable of predicting the level of economic success.

Researching the Influence of Peer-Reviews in Action Movies Based on Public Opinion

Our goal is to be able to answer the questions that have arisen because of our research, "Which characteristics make internet reviews useful?" To address this issue, we used douban.com, a prominent consumer movie review site, to gather online movie reviews. This research creates an internet effect factor reviews framework using data mining methods. The findings show that article qualities do have an impact on users' judgments of intervention effectiveness. The duration of online reviews, optimistic attitude, severe emotional inclination, and review reliability all have a significant beneficial influence on the effectiveness of reviews. Moreover, happy emotions are more beneficial and powerful than bad emotions. The findings also imply that review number moderates the association between online reviews’ high emotional inclination and their effectiveness. The research gives insight into how people assess online reviews, and the results may aid professionals in developing methods that utilize reviews to forecast commercial success in the market.

Researching the Influence of Peer-Reviews in Action Movies Based on Public Opinion

Our goal is to be able to answer the questions that have arisen because of our research, "Which characteristics make internet reviews useful?" To address this issue, we used douban.com, a prominent consumer movie review site, to gather online movie reviews. This research creates an internet effect factor reviews framework using data mining methods. The findings show that article qualities do have an impact on users' judgments of intervention effectiveness. The duration of online reviews, optimistic attitude, severe emotional inclination, and review reliability all have a significant beneficial influence on the effectiveness of reviews. Moreover, happy emotions are more beneficial and powerful than bad emotions. The findings also imply that review number moderates the association between online reviews’ high emotional inclination and their effectiveness. The research gives insight into how people assess online reviews, and the results may aid professionals in developing methods that utilize reviews to forecast commercial success in the market.

Online movie review as a person-oriented type of discourse

The article examines the features of the presence of a person-oriented type of discourse in the online movie review written in English. Personal discourse in itself covers almost all text types generated by the Internet due to the presence of various verbal and non-verbal means of converging the addressee of the communicative message. The variety of linguistic characteristics of disclosing the inner world of a person, verbal means of expressing interpersonal relations, lexical means of explicating the category of a person and other way of linguistic representation of the author's self determine the consideration of online movie reviews as a person-oriented type of discourse. The aim of this article is to analyze the linguistic means of manifestation the personal discourse in the English-language amateur movie review. The empirical material collected for description, classification and analysis in this paper is based upon a corpus of movie reviews taken from the American review-aggregation website for film and television Rotten Tomatoes. The person-oriented type of discourse is intrinsically inherent in the online movie review due to its fundamentally dialogic nature and the low level of formalization of the communicative message. The analysis of the online movie reviews has revealed that the attributive feature of the deployment of personal discourse in the online movie review is a statement that carries subjective modality. Personal and demonstrative pronouns in conjunction with modal words, verbs and particles are those lexical means which express a subjective attitude towards the film. The explicators of the modal-evaluative meanings in the online movie review are parenthesis and inversion. In addition to emotional and expressive vocabulary, the personal discourse of online movie reviews manifests itself in the widespread use of colloquial vocabulary.

Effects of Sentiment Analysis on Feedback Loops between Different Types of Movies

This research was conducted with the intention of determining the specific qualities of internet reviews that contributed to their usefulness. The collected online movie reviews were found on the website Rotten Tomatoes, which is dedicated to film criticism. The methodology for conducting online reviews of impact factors that was developed as a result of this research makes use of data mining techniques. According to the findings of one study, users' perceptions of the efficacy of interventions are influenced by the quality of the articles. The effectiveness of a reviewer's contributions is increased when they are in a good mood, have a strong emotional predisposition, and a high degree of review reliability. On the other hand, negative emotions are both less beneficial and weaker than their positive counterparts. It has been demonstrated that emotionally charged evaluations receive a greater number of reviews and have a tendency to be more effective. The findings of this research, which investigated the manner in which individuals evaluate online reviews, could assist in the development of novel methods that are capable of predicting the level of economic success.

Emotions for attention in online consumer reviews: the moderated mediating role of review helpfulness

PurposeWith the increasing importance of e-commerce to the economy and people's lives, user-generated content, such as electronic word-of-mouth (eWOM) represented by online reviews, has exploded. On one hand, it is of great significance for review consumers (readers) to identify high-quality ones from a large number of existing reviews to assist their purchase decision. On the other hand, how to use appropriate strategies to make their published reviews more concerned by others is also important to review generators (reviewers). The purpose of this study is to understand the comprehensive relationship among review characteristics, review helpfulness and receiver attention.Design/methodology/approachThis study uses the online movie reviews obtained from the most popular review platform in China to conduct multiple empirical analyses.FindingsThe results show that the review helpfulness plays a mediating role between the emotional characteristics of online reviews and the receiver attention, and such a mediating role is more significant among reviewers with rich review expertise. The reviewer's expertise also moderates the impact of review emotions on review helpfulness.Originality/valueThis work studies eWOM receiver involvement, which can ultimately impact product sales, but seldom be investigated in eWOM domain. Therefore, this research can enrich studies on eWOM and provide valuable practical implications as well.

A study of the relationship between online movie reviews and the intention to watch the movie

Aim/purpose – This study explores how the content feature and source of eWOM affect people’s intentions and further analyses the effectiveness of eWOM on people’s inten- tion to watch movies. Design/methodology/approach – The study considers two dimensions of movie reviews, including the source (anonymous or acquaintance) and the content feature (con- crete or abstract), adopts a 2x2 between-subject design, and then analyzes online ques- tionnaires (N = 313) via statistics analysis methods. Findings – The findings showed that if the source is from an acquaintance and the con- tent feature is concrete, then people will have the highest intention to watch the movie. In addition, the acting skills of the cast and the love of the movie genre also enhance the positive influence on the viewer’s experience. Research implications/limitations – The respondents were selected only in Taiwan so this paper do not explain any differences among different countries. For example, cultur- al differences exist between the West and the East in the content feature of eWOM. Originality/value/contribution – If a type of genre is greatly accepted by the audience and generates huge box-office revenue, then producers and movie companies might keep making movies in these kinds of genre to secure profits. Therefore, box-office movies will usually fall into these certain types of genres, and there will be an abundance of them released in the near future. Keywords: source of eWOM, content feature of eWOM, online movie review, between- -subject design. JEL Classification: C12, C90.

СПОСОБЫ РЕАЛИЗАЦИИ КАТЕГОРИИ АРГУМЕНТАТИВНОСТИ В АНГЛОЯЗЫЧНОЙ СЕТЕВОЙ КИНОРЕЦЕНЗИИ

This article discusses how the category of argumentativeness is employed in online movie reviews written in English. The objectives of the study were to consider the concepts of argumentation and argumentativeness, to define the categories of argumentativeness and evaluativeness as the constituents of a movie review, as well as to identify the lexical-semantic, stylistic, and structural-syntactic parameters of the argumentative discourse expressed in an online movie review. The validity and reliability of the ways used to process the material under study were ensured by the correct application of the following modern methods of linguistic analysis: structural-semantic, interpretative, and functional-stylistic. A number of examples were provided, all proving that the development of the author’s thesis occurs both explicitly (owing to the presence of the thesis and at least two arguments, linking words, introductory phrases, parenthesis) and implicitly (through to the question-answer form of presentation, irony, sarcasm, and using of numerous personal pronouns). The results obtained show that conjunctions play a significant role in the development of the argumentative discourse: firstly, coordinating conjunctions (such as and, so, but) introduce the thesis; secondly, subordinating conjunctions (for example, because, since, as) introduce arguments serving to put forward the thesis. It was concluded that the argumentative discourse in the text of a movie review explicitly manifests itself through such lexical means used to express the category of cohesion (transition from one segment to another while maintaining both structural and semantic unity) as in the first place, for example, then, plus, finally, etc. It was also revealed that any “incorporations” of other discourses, which are markers of a causal interdiscursive strategy, have an argumentative potential in the text of a movie review and fall into two categories: references to the director’s previous works; references to films of other directors. The results of this study are important for developing modern genre studies and the theory of speech acts.

Sentiment Analysis of Online Movie Reviews using Machine Learning

Many websites encourage their users to write reviews for a wide variety of products and services. In particular, movie reviews may influence the decisions of potential viewers. However, users face the arduous tasks of summarizing the information in multiple reviews and determining the useful and relevant reviews among a very large number of reviews. Therefore, we developed machine learning (ML) models to classify whether an online movie review has positive or negative sentiment. We utilized the Stanford Large Movie Review Dataset to build models using decision trees, random forests, and support vector machines (SVMs). Further, we compiled a new dataset comprising reviews from IMDb posted in 2019 and 2020 to assess whether sentiment changed owing to the coronavirus disease 2019 (COVID-19) pandemic. Our results show that the random forests and SVM models provide the best classification accuracies of 85.27% and 86.18%, respectively. Further, we find that movie reviews became more negative in 2020. However, statistical tests show that this change in sentiment cannot be discerned from our model predictions.