Content-Based Collaborative Filtering using Word Embedding

Nguyen, Luong Vuong; Nguyen, Tri-Hai; Jung, Jason J.

doi:10.1145/3400286.3418253

Cited by 27 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, natural language processing methods have been used to computationally study and classify films [66][67][68][69], film reviews, being an important industry feedback component [70][71][72], social media coverage of festivals [73], and gender bias in synopses and scripts [74]. Inferring and making use of film metadata and characteristics [75], as well as viewer activity [76,77], has been a central interest of recommendation systems research, more so with the commercial importance stemming from increasing platformization, and digitalization of the film industry in general [78]. In contrast to most of the aforementioned research, and to the survey-focused event and festival research [9], here we focus on festivals as the primary unit of analysis but use available film metadata to construct festival profiles.…”

Section: Quantifying Festivals Using Metadata Embeddingsmentioning

confidence: 99%

Quantifying the global film festival circuit: Networks, diversity, and public value creation

Zemaityte¹,

Karjus²,

Rohn³

et al. 2023

Preprint

View full text Add to dashboard Cite

Film festivals are a key component in the global film industry in terms of trendsetting, publicity, trade, and collaboration. We present an unprecedented analysis of the international film festival circuit, which has so far remained relatively understudied quantitatively, partly due to the limited availability of suitable data sets. We use large-scale data from the Cinando platform of the Cannes Film Market, widely used by industry professionals. We explicitly model festival events as a global network connected by shared films, and quantify festivals as aggregates of the metadata of their showcased films. Importantly, we argue against using simple count distributions for discrete labels such as language or production country, as such categories are typically not equidistant. Rather, we propose embedding them in continuous latent vector spaces. We demonstrate how these “festival embeddings” provide insight into changes in programmed content over time, predict festival connections, and can be used to measure diversity in film festival programming across various cultural, social, and geographical variables---which all constitute an aspect of public value creation by film festivals. Our results provide a novel mapping of the film festival circuit between 2009--2021 (616 festivals, 31,989 unique films), highlighting festival types that occupy specific niches, diverse series, and those that evolve over time. We also discuss how these quantitative findings fit into media studies and research on public value creation by cultural industries. With festivals occupying a central position in the film industry, investigations into the data they generate hold opportunities for researchers to better understand industry dynamics and cultural impact, and for organizers, policymakers, and industry actors to make more informed, data-driven decisions. We hope our proposed methodological approach to festival data paves way for more comprehensive film festival studies and large-scale quantitative cultural event analytics in general.

show abstract

Section: Quantifying Festivals Using Metadata Embeddingsmentioning

confidence: 99%

Quantifying the global film festival circuit: Networks, diversity, and public value creation

Zemaityte¹,

Karjus²,

Rohn³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The features extracted are the titles, genres, directors, actors, and content plots, which are readily available. By applying the Word2Vec embedding model, 18 we create a semantic vector for the plot of every movie and measure the similarity between these vectors. We represent the user–item interactions by combining the plot similarity with the similarities of the remaining features to investigate their relations and make recommendations.…”

Section: Background and Related Workmentioning

confidence: 99%

Extending collaborative filtering recommendation using word embedding: A hybrid approach

Nguyen

Jung

et al. 2021

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Summary Collaborative filtering recommendation systems, which analyze sets of user ratings, have been applied to various domains and have resulted in considerable improvements in the traditional recommendation system. However, they still have problems with data sparsity and cold‐start of the user ratings. To solve these problems, we present a hybrid recommendation approach by combining collaborative filtering methods and word embedding‐based content analysis. This study focuses on the movie domain, and therefore, the contents of the items are represented as a set of features such as titles, genres, directors, actors, and plots. The main aim of this paper is to understand the content of the movie plot using a word embedding to improve the measurement of similarity of each plot content to other plot content (called plot embedding). To enhance the accuracy in measuring the similarity between movies, we also consider other features such as titles, genres, directors, and actors extracted from movies. In the experiments, the movie dataset was collected by our crowdsourcing platform, which is the OMS platform. The experimental findings indicate that the proposed approach can enhance the efficiency of applied collaborative filtering recommendation systems.

show abstract

“…However, recent studies have identified several drawbacks and challenges that need to be addressed. One significant problem is the cold start issue, where the system struggles to make recommendations for new items or users with no prior interaction history, resulting in poor performance and usability for novice users [5,6]. To overcome this challenge, innovative strategies such as a hybrid recommendation system combining collaborative filtering with content-based algorithms and performance enhancements are being developed [2,4,5].…”

Section: Introductionmentioning

confidence: 99%

Adaptive KNN-Based Extended Collaborative Filtering Recommendation Services

Nguyen

2023

BDCC

Self Cite

View full text Add to dashboard Cite

In the current era of e-commerce, users are overwhelmed with countless products, making it difficult to find relevant items. Recommendation systems generate suggestions based on user preferences, to avoid information overload. Collaborative filtering is a widely used model in modern recommendation systems. Despite its popularity, collaborative filtering has limitations that researchers aim to overcome. In this paper, we enhance the K-nearest neighbor (KNN)-based collaborative filtering algorithm for a recommendation system, by considering the similarity of user cognition. This enhancement aimed to improve the accuracy in grouping users and generating more relevant recommendations for the active user. The experimental results showed that the proposed model outperformed benchmark models, in terms of MAE, RMSE, MAP, and NDCG metrics.

show abstract

Content-Based Collaborative Filtering using Word Embedding

Cited by 27 publications

References 15 publications

Quantifying the global film festival circuit: Networks, diversity, and public value creation

Quantifying the global film festival circuit: Networks, diversity, and public value creation

Extending collaborative filtering recommendation using word embedding: A hybrid approach

Adaptive KNN-Based Extended Collaborative Filtering Recommendation Services

Contact Info

Product

Resources

About