Leveraging genre classification with RNN for Book recommendation

Saraswat, Mala; Srishti, .

doi:10.1007/s41870-022-00937-6

Cited by 18 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BILSTM [30] is a type of RNN (Recurrent Neural Network) [28] that addresses the challenge of gradient vanishing and exploding during training. In this study, LSTM is to classify words, CRF (Conditional Random Field) [29], and continuously obtain restrictive rules from the training data to ensure the predicted labels.…”

Section: Bilstm Algorithmmentioning

confidence: 99%

Design of agricultural question answering information extraction method based on improved LSTM algorithm

Tang,

Aridas,

Talip

2024

Preprint

View full text Add to dashboard Cite

With the rapid growth of the agricultural information and the need for data analysis, how to accurately extract useful information from massive data has become an urgent first step in agricultural data mining and application. In this study, an agricultural question-answering information extraction method based on the IM-BILSTM (Improved Bidirectional Long Short-Term Memory) algorithm is designed. Firstly, it uses Python's Scrapy crawler framework to obtain the imformation of soil types, crop diseases and pests, and agricultural trade information, and remove abnormal values. Secondly, the information extraction converts the semi-structured data by using entity extraction methods. Thirdly, the BERT(Bidirectional Encoder Representations from Transformers) algorithm is introduced to improve the performance of the BILSTM algorithm. After comparing with the BERT-CRF(Conditional Random Field) and BILSTM algorithm, the result shows that the IM-BILSTM algorithm has better information extraction performance than the other two algorithms. This study improves the accuracy of the agricultural information recommendation system from the perspective of information extraction. Compared with other work that is done from the perspective of recommendation algorithm optimization, it is more innovative; it helps to understand the semantics and contextual relationships in agricultural question and answer, so as to Improve the accuracy of agricultural information recommendation systems. By gaining a deeper understanding of farmers' needs and interests, the system can better recommend relevant and practical information.

show abstract

Section: Bilstm Algorithmmentioning

confidence: 99%

Design of agricultural question answering information extraction method based on improved LSTM algorithm

Tang,

Aridas,

Talip

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The work of [19] uses Recurrent Neural Networks (RNNs) as a deep learning method to classify book plots and reviews. The successful classification of 28 genres, including action, adventure, comedy, drama, family, mystery, romance, and science, is demonstrated by the testing findings.…”

Section: Related Workmentioning

confidence: 99%

Genre Classification of Books in Russian with Stylometric Features: A Case Study

Vanetik,

Tiamanova,

Kogan

et al. 2024

Information

View full text Add to dashboard Cite

Within the literary domain, genres function as fundamental organizing concepts that provide readers, publishers, and academics with a unified framework. Genres are discrete categories that are distinguished by common stylistic, thematic, and structural components. They facilitate the categorization process and improve our understanding of a wide range of literary expressions. In this paper, we introduce a new dataset for genre classification of Russian books, covering 11 literary genres. We also perform dataset evaluation for the tasks of binary and multi-class genre identification. Through extensive experimentation and analysis, we explore the effectiveness of different text representations, including stylometric features, in genre classification. Our findings clarify the challenges present in classifying Russian literature by genre, revealing insights into the performance of different models across various genres. Furthermore, we address several research questions regarding the difficulty of multi-class classification compared to binary classification, and the impact of stylometric features on classification accuracy.

show abstract

“…This model uniquely leverages the semantic signals emanating from user reviews to encapsulate user inclinations. In 2022, Saraswat and Srishti [9] presented a novel approach utilising user-generated comments about books. They ingeniously categorised book plots and user reviews into distinctive categories and harnessed the power of RNNs to decode users' evolving preferences.…”

Section: Heterogeneous Features In Sequential Recommendationmentioning

confidence: 99%

“…Therefore, in modelling user preferences, some recently proposed models have begun incorporating information beyond the item ID [8][9][10], like textual descriptions of the item features, including user reviews. While user-generated reviews have been shown to enhance recommendation results somewhat, many applications, such as Netflix, only offer implicit feedback (with no review data available).…”

Section: Introductionmentioning

confidence: 99%

Improving Sequential Recommendation Performance with a Hybrid Timed GRU Framework

Sun,

Yan,

Ren

2023

Preprint

View full text Add to dashboard Cite

Recently, significant progress has been made in sequential recommendations with deep learning techniques. The key to the sequential recommendation lies in delving into users' sequence interaction histories to discern their preferences, as such continuous behaviours manifest the dynamic evolution of user inclinations. Most existing Recurrent neural network (RNN)-based methods focus solely on item IDs to capture users’ sequential preferences, neglecting the intricate interrelationships among the user-interacted item features when simulating the user's preference dynamic. This oversight causes them to be less adept at capturing the drifts in users' interests at the item or feature level. To address this limitation, we introduce a feature-level modelling framework into the traditional RNN-based sequential recommendation model, effectively utilizing item features on top of methods that rely solely on sequential patterns. Specifically, in our proposed model, users' preferences are constituted by their feature-level and sequential preferences. These two types of preferences are feed into different time-sensitive Gated Recurrent Unit (GRU) modules (named 2TGRU) in a parallel structure to study the interrelationships between users, items, and features, highlighting the importance of these two distinct types of preferences in user modelling. We have named this model Hybrid-2TGRU. Validated on three real-world datasets, including movies and Points of Interest (POI), the model's recommendation accuracy, which considers user preferences at the feature level, has been confirmed. Experimental results show that Hybrid-2TGRU effectively combines users' sequential preferences with feature-level preferences, enabling complementary user preference modelling and enhancing recommendation performance.

show abstract

Leveraging genre classification with RNN for Book recommendation

Cited by 18 publications

References 16 publications

Design of agricultural question answering information extraction method based on improved LSTM algorithm

Design of agricultural question answering information extraction method based on improved LSTM algorithm

Genre Classification of Books in Russian with Stylometric Features: A Case Study

Improving Sequential Recommendation Performance with a Hybrid Timed GRU Framework

Contact Info

Product

Resources

About