Search results

In this “Info-plosion” era, recommendation systems (or recommenders) play a significant role in finding interesting items in the surge of online digital activity and e-commerce. The purpose of this paper is to model users' preference evolution to recommend potential items which users may be interested in.

A novel recommendation system, namely evolution-learning recommendation (ELR), is developed to precisely predict user interest for making recommendations. Differing from prior related methods, the authors integrate the matrix factorization (MF) and recurrent neural network (RNN) to effectively describe the variation of user preferences over time.

A novel cumulative factorization technique is proposed to efficiently decompose a rating matrix for discovering latent user preferences. Compared to traditional MF-based methods, the cumulative MF could reduce the utilization of computation resources. Furthermore, the authors depict the significance of long- and short-term effects in the memory cell of RNN for evolution patterns. With the context awareness, a learning model, V-LSTM, is developed to dynamically capture the evolution pattern of user interests. By using a well-trained learning model, the authors predict future user preferences and recommend related items.

Based on the relations among users and items for recommendation, the authors introduce a novel concept, virtual communication, to effectively learn and estimate the correlation among users and items. By incorporating the discovered latent features of users and items in an evolved manner, the proposed ELR model could promote “right” things to “right” users at the “right” time. In addition, several extensive experiments are performed on real datasets and are discussed. Empirical results show that ELR significantly outperforms the prior recommendation models. The proposed ELR exhibits great generalization and robustness in real datasets, including e-commerce, industrial retail and streaming service, with all discussed metrics.

The purpose of this study is to investigate how book group recommendations can be used as a meaningful way to suggest suitable books to users, given the increasing number of individuals engaging in sharing and discussing books on the web.

The authors propose reviews fine-grained classification (CFGC) and its related models such as CFGC1 for book group recommendation. These models can categorize reviews successively by function and role. Constructing the BERT-BiLSTM model to classify the reviews by function. The frequency characteristics of the reviews are mined by word frequency analysis, and the relationship between reviews and total book score is mined by correlation analysis. Then, the reviews are classified into three roles: celebrity, general and passerby. Finally, the authors can form user groups, mine group features and combine group features with book fine-grained ratings to make book group recommendations.

Overall, the best recommendations are made by Synopsis comments, with the accuracy, recall, F-value and Hellinger distance of 52.9%, 60.0%, 56.3% and 0.163, respectively. The F1 index of the recommendations based on the author and the writing comments is improved by 2.5% and 0.4%, respectively, compared to the Synopsis comments.

Previous studies on book recommendation often recommend relevant books for users by mining the similarity between books, so the set of book recommendations recommended to users, especially to groups, always focuses on the few types. The proposed method can effectively ensure the diversity of recommendations by mining users’ tendency to different review attributes of books and recommending books for the groups. In addition, this study also investigates which types of reviews should be used to make book recommendations when targeting groups with specific tendencies.

Given the critical role of user-generated content (UGC) in e-commerce, exploring various aspects of UGC can aid in understanding user purchase intention and commodity recommendation. Therefore, this study investigates the impact of UGC on purchase decisions and proposes new recommendation models based on sentiment analysis, which are verified in Douban, one of the most popular UGC websites in China.

After verifying the relationship between various factors and product sales, this study proposes two models, collaborative filtering recommendation model based on sentiment (SCF) and hidden factors topics recommendation model based on sentiment (SHFT), by combining traditional collaborative filtering model (CF) and hidden factors topics model (HFT) with sentiment analysis.

The results indicate that sentiment significantly influences purchase intention. Furthermore, the proposed sentiment-based recommendation models outperform traditional CF and HFT in terms of mean absolute error (MAE) and root mean square error (RMSE). Moreover, the two models yield different outcomes for various product categories, providing actionable insights for organizers to implement more precise recommendation strategies.

The findings of this study advocate the incorporation of UGC sentimental factors into websites to heighten recommendation accuracy. Additionally, different recommendation strategies can be employed for different products types.

This study introduces a novel perspective to the recommendation algorithm field. It not only validates the impact of UGC sentiment on purchase intention but also evaluates the proposed models with real-world data. The study provides valuable insights for managerial decision-making aimed at enhancing recommendation systems.

Artificial intelligence (AI) is revolutionizing product recommendations, but little is known about consumer acceptance of AI recommendations. This study examines how to improve consumers' acceptance of AI recommendations from the perspective of product type (material vs experiential).

Four studies, including a field experiment and three online experiments, tested how consumers' preference for AI-based (vs human) recommendations differs between material and experiential product purchases.

Results show that people perceive AI recommendations as more competent than human recommendations for material products, whereas they believe human recommendations are more competent than AI recommendations for experiential products. Therefore, people are more (less) likely to choose AI recommendations when buying material (vs experiential) products. However, this effect is eliminated when is used as an assistant to rather than a replacement for a human recommendation.

This study is the first to focus on how products' material and experiential attributes influence people's attitudes toward AI recommendations. The authors also identify under what circumstances resistance to algorithmic advice is attenuated. These findings contribute to the research on the psychology of artificial intelligence and on human–technology interaction by investigating how experiential and material attributes influence preference for or resistance to AI recommenders.

This study aims to explore the application of emojis to mood descriptions of fiction. The three goals are investigating whether Cho et al.'s model (2023) is a sound conceptual framework for implementing emojis and mood categories in information systems, mapping 30 mood categories to 115 face emojis and exploring and visualizing the relationships between mood categories based on emojis mapping.

An online survey was distributed to a US public university to recruit adult fiction readers. In total, 64 participants completed the survey.

The results show that the participants distinguished between the three families of fiction mood categories. The three families model is a promising option to improve mood descriptions for fiction. Through mapping emojis to 30 mood categories, the authors identified the most popular emojis for each category, analyzed the relationships between mood categories and examined participants' consensus on mapping.

This study focuses on applying emojis to fiction reading. Emojis were mapped to mood categories by fiction readers. Emoji mapping contributes to the understanding of the relationships between mood categories. Emojis, as graphic mood descriptors, have the potential to complement textual descriptors and enrich mood metadata for fiction.

Traditional library book recommendation methods are mainly based on association rules and user profiles. They may help to learn about students' interest in different types of books, e.g., students majoring in science and engineering tend to pay more attention to computer books. Nevertheless, most of them still need to identify users' interests accurately. To solve the problem, the authors propose a novel embedding-driven model called InFo, which refers to users' intrinsic interests and academic preferences to provide personalized library book recommendations.

The authors analyze the characteristics and challenges in real library book recommendations and then propose a method considering feature interactions. Specifically, the authors leverage the attention unit to extract students' preferences for different categories of books from their borrowing history, after which we feed the unit into the Factorization Machine with other context-aware features to learn students' hybrid interests. The authors employ a convolution neural network to extract high-order correlations among feature maps which are obtained by the outer product between feature embeddings.

The authors evaluate the model by conducting experiments on a real-world dataset in one university. The results show that the model outperforms other state-of-the-art methods in terms of two metrics called Recall and NDCG.

It requires a specific data size to prevent overfitting during model training, and the proposed method may face the user/item cold-start challenge.

The embedding-driven book recommendation model could be applied in real libraries to provide valuable recommendations based on readers' preferences.

The proposed method is a practical embedding-driven model that accurately captures diverse user preferences.

Readers articulate mood in deeply subjective ways, yet the underlying structure of users' understanding of the media they consume has important implications for retrieval and access. User articulations might at first seem too idiosyncratic, but organizing them meaningfully has considerable potential to provide a better searching experience for all involved. The current study develops mood categories inductively for fiction organization and retrieval in information systems.

The authors developed and distributed an open-ended survey to 76 fiction readers to understand their preferences with regard to the affective elements in fiction. From the fiction reader responses, the research team identified 161 mood terms and used them for further categorization.

The inductive approach resulted in 30 categories, including angry, cozy, dark and nostalgic. Results include three overlapping mood families: Emotion, Tone/Narrative, and Atmosphere/Setting, which in turn relate to structures that connect reader-generated data with conceptual frameworks in previous studies.

The inherent complexity of “mood” should not dissuade researchers from carefully investigating users' preferences in this regard. Adding to the existing efforts of classifying moods conducted by experts, the current study presents mood terms provided by actual end-users when describing different moods in fiction. This study offers a useful roadmap for creating taxonomies for retrieval and description, as well as structures derived from user-provided terms that ultimately have the potential to improve user experience.

For a better understanding of the preferences and differences of young consumers in emerging wine markets, this study aims to propose a clustering method to segment the super-new generation wine consumers based on their sensitivity to wine brand, origin and price and then conduct user profiles for segmented consumer groups from the perspectives of demographic attributes, eating habits and wine sensory attribute preferences.

We first proposed a consumer clustering perspective based on their sensitivity to wine brand, origin and price and then conducted an adaptive density peak and label propagation layer-by-layer (ADPLP) clustering algorithm to segment consumers, which improved the issues of wrong centers' selection and inaccurate classification of remaining sample points for traditional DPC (DPeak clustering algorithm). Then, we built a consumer profile system from the perspectives of demographic attributes, eating habits and wine sensory attribute preferences for segmented consumer groups.

In this study, 10 typical public datasets and 6 basic test algorithms are used to evaluate the proposed method, and the results showed that the ADPLP algorithm was optimal or suboptimal on 10 datasets with accuracy above 0.78. The average improvement in accuracy over the base DPC algorithm is 0.184. As an outcome of the wine consumer profiles, sensitive consumers prefer wines with medium prices of 100–400 CNY and more personalized brands and origins, while casual consumers are fond of popular brands, popular origins and low prices within 50 CNY. The wine sensory attributes preferred by super-new generation consumers are red, semi-dry, semi-sweet, still, fresh tasting, fruity, floral and low acid.

Young Chinese consumers are the main driver of wine consumption in the future. This paper provides a tool for decision-makers and marketers to identify the preferences of young consumers quickly which is meaningful and helpful for wine marketing.

In this study, the ADPLP algorithm was introduced for the first time. Subsequently, the user profile label system was constructed for segmented consumers to highlight their characteristics and demand partiality from three aspects: demographic characteristics, consumers' eating habits and consumers' preferences for wine attributes. Moreover, the ADPLP algorithm can be considered for user profiles on other alcoholic products.

Recent archiving and curatorial practices took advantage of the advancement in digital technologies, creating immersive and interactive experiences to emphasize the plurality of memory materials, encourage personalized sense-making and extract, manage and share the ever-growing surrounding knowledge. Audiovisual (AV) content, with its growing importance and popularity, is less explored on that end than texts and images. This paper examines the trend of datafication in AV archives and answers the critical question, “What to extract from AV materials and why?”.

This study roots in a comprehensive state-of-the-art review of digital methods and curatorial practices in AV archives. The thinking model for mapping AV archive data to purposes is based on pre-existing models for understanding multimedia content and metadata standards.

The thinking model connects AV content descriptors (data perspective) and purposes (curatorial perspective) and provides a theoretical map of how information extracted from AV archives should be fused and embedded for memory institutions. The model is constructed by looking into the three broad dimensions of audiovisual content – archival, affective and aesthetic, social and historical.

This paper contributes uniquely to the intersection of computational archives, audiovisual content and public sense-making experiences. It provides updates and insights to work towards datafied AV archives and cope with the increasing needs in the sense-making end using AV archives.

The purpose of this study is to identify the knowledge gap and future opportunities for developing mobile recommender system in tourism sector that lead to comfortable, targeted and attractive tourism. A recommender system improves the traditional classification algorithms and has incorporated many advanced machine learning algorithms.

Design of this application followed a smart, hybrid and context-aware recommender system, which includes various recommender systems. With the recommender system's help, useful management for time and budget is obtained for tourists, since they usually have financial and time constraints for selecting the point of interests (POIs) and so more purposeful trip planned with decreased traffic and air pollution.

The finding of this research showed that the inclusion of additional information about the item, user, circumstances, objects or conditions and the environment could significantly impact recommendation quality and information and communications technology has become one part of the tourism value chain.

The application consists of (1) registration: with/without social media accounts, (2) user information: country, gender, age and his/her specific interests, (3) context data: available time, alert, price, spend time, weather, location, transportation.

The study’s social implications include connecting the app and registration through social media to a more social relationship, with its textual reviews, or user review as user-generated content for increasing accuracy.

The originality of this research work lies on introducing a new content- and knowledge-based algorithm for POI recommendations. An “Alert” context emphasizing on safety, supplies and essential infrastructure is considered as a novel context for this application.