Group Recommendations Research Articles

Methods of preference aggregation in group recommender systems

The rapid growth of data volumes has led to information overload, which impedes informed decision-making. To solve this problem, recommender systems have emerged that analyze user preferences and offer relevant products on their own. One type of recommender system is group recommender systems, which are designed to facilitate collaborative decision-making, increase user engagement, and promote diversity and inclusion. However, these systems face challenges such as accommodating diverse group preferences and maintaining transparency in recommendation processes. In this study, we propose a method for aggregating preferences in group recommendation systems to retain as much information as possible from group members and improve the accuracy of recommendations. The proposed method provides recommendations to groups of users by avoiding the aggregation process in the first steps of recommendation, which preserves information throughout the group recommendation process and delays the aggregation step to provide accurate and diverse recommendations. When the object of a collaborative filtering-based recommender system is not a single user but a group of users, the strategy for calculating similarity between individual users to find similarity should be adapted to avoid aggregating the preferences of group members in the first step. In the proposed model, the nearest neighbors of a group of users are searched, so the method of finding neighbors is adapted to compare individual users with the group profile. An experimental study has shown that the proposed method achieves a satisfactory balance between accuracy and diversity. This makes it well suited for providing recommendations to large groups in situations where accuracy is more or less important compared to diversity. These results support the assumption that retaining all information from group members without using aggregation techniques can improve the performance of group recommender systems, taking into account various features.

Leveraging item attribute popularity for group recommendation

Leveraging item attribute popularity for group recommendation

Needs and experiences of homecare workers when supporting people to live at home at the end of life: a rapid review

BackgroundSocial homecare workers provide essential care to those living at home at the end of life. In the context of a service experiencing difficulties in attracting and retaining staff, we...

Point-of-Care Ultrasound (POCUS) Training Curriculum for Pediatric Nephrology: PCRRT-ICONIC Group Recommendations.

Point of care ultrasound (POCUS) is commonly used in adult specialties, pediatric emergency medicine, and neonatal and pediatric critical care. Specifically, in the field of pediatric nephrology, POCUS plays a valuable role in the critical inpatient and outpatient settings. However, the lack of guidelines and a standardized curriculum for POCUS in pediatric nephrology has led to substantial discrepancies in both clinical practice and training. A multinational, multicenter survey regarding POCUS usefulness and training was sent to 225 pediatric nephrology residents, fellows, and physicians with expertise in pediatric nephrology. Based on the results, an ideal pediatric nephrology POCUS curriculum was formulated with a panel of experts from across the world. Eighteen experts were included, with each expert having greater than 10 years of experience in using POCUS in adult and pediatric nephrology. A Delphi method was utilized to further solidify guidelines regarding the content, curriculum, and vital skills of using POCUS in pediatric nephrology. A total of 134 pediatric nephrology trainees, specialists, and faculty responded to the survey (59.6% completion rate). A total of 87.4% of respondents believe that formal POCUS training is either highly desirable or should be mandatory in pediatric nephrology fellowship programs. Identified barriers to receiving training included lack of an organized curriculum, lack of POCUS experts and Pediatric intensivists, lack of ultrasound equipment, lack of financial support, and lack of dedicated time during training. An expert panel was convened and a Delphi survey was conducted to formulate guidelines to overcome the barriers to pediatric nephrology POCUS and standardize the training process. After collaborating with prominent pediatric nephrologists and global POCUS experts proposed a comprehensive POCUS training curriculum tailored specifically for pediatric nephrology trainees, with an appeal for all pediatric nephrology education programs to integrate POCUS instruction into their curricula.

Perioperative pain optimization in the age of the opioid epidemic.

The opioid epidemic remains a constant and increasing threat to our society with overdoses and overdose deaths rising significantly during the COVID-19 pandemic. Growing evidence suggests a link between perioperative opioid use, postoperative opioid prescribing, and the development of opioid use disorder (OUD). As a result, strategies to better optimize pain management during the perioperative period are urgently needed. The purpose of this review is to summarize the most recent multimodal analgesia (MMA) recommendations, summarize evidence for efficacy surrounding the increased utilization of Enhanced Recovery After Surgery (ERAS) protocols, and discuss the implications for rising use of buprenorphine for OUD patients who present for surgery. In addition, this review will explore opportunities to expand our treatment of complex patients via transitional pain services. There is ample evidence to support the benefits of MMA. However, optimal drug combinations remain understudied, presenting a target area for future research. ERAS protocols provide a more systematic and targeted approach for implementing MMA. ERAS protocols also allow for a more comprehensive approach to perioperative pain management by necessitating the involvement of surgical specialists. Increasingly, OUD patients taking buprenorphine are presenting for surgery. Recent guidance from a multisociety OUD working group recommends that buprenorphine not be routinely discontinued or tapered perioperatively. Lastly, there is emerging evidence to justify the use of transitional pain services for more comprehensive treatment of complex patients, like those with chronic pain, preoperative opioid tolerance, or substance use disorder. Perioperative physicians must be aware of the impact of the opioid epidemic and explore methods like MMA techniques, ERAS protocols, and transitional pain services to improve the perioperative pain experience and decrease the risks of opioid-related harm.

The assessment of tumor-infiltrating lymphocytes in invasive apocrine carcinoma of the breast in relation to the HER2 status.

In the current study, we assessed the prevalence and molecular features of HER2-low phenotype in the apocrine carcinomas of the breast (ApoCa) and its relationship with tumor-infiltrating lymphocytes (TILs). A cohort of 64 well-characterized therapy-naïve ApoCa was used. The TIL distribution was assessed using the hematoxylin and eosin whole slide/scanned images following the international TILs working group recommendations. Next-generation sequencing (NGS) was performed in a subset of HER2-low ApoCa. All patients were women, with a mean age of 62 years. Forty-three carcinomas were pure apocrine carcinoma (PAC; ER-/AR+), and the remaining 21 were classified as apocrine-like carcinomas (ALCs; ER+/-, AR+/-). HER2/neu was positive (score 3+ by IHC and/or amplified by FISH) in 20/43 (47%) PAC and 4/21 (19%) ALC. The prevalence of HER2-low expression (scores 1+ or 2+ without HER2 amplification) in ApoCa was 39% without significant differences between PAC and ALC (P = 0.14); however, the HER2-low phenotype was more prevalent in triple-negative PAC than in ALC (P < 0.001). Levels of TILs were low (≤10%) in 74% of ApoCa (median 5%, range 0%-50%). TIL levels were significantly higher in ALC than in PAC (P = 0.02). HER2 status had no impact on TIL distribution (P = 0.45). The genomic profile of HER2-low ApoCa was similar to other subtypes of ApoCa. ApoCa has predominantly low TIL, particularly PAC.The prevalence of the HER2-low phenotype in ApoCa is high, which should have therapeutic and clinical implications given the recently approved therapies with antibody-drug conjugates (ADCs) for HER2-low breast cancers.

New opportunities for correction of hormonal disorders and oxidative stress in women with genital endometriosis

Background. Genital endometriosis is one of the most urgent problems of modern gynecology. Considering oxidative stress as a pathogenetic link of endometriosis, we believe it reasonable to use a combined drug containing superoxide dismutase, resveratrol, and zinc. The purpose of the work was to evaluate the effectiveness of the treatment for genital endometriosis supplemented with the use of superoxide dismutase, resveratrol, and zinc, taking into account the leading pathophysiological links of the pathology. Materials and methods. Thirty-seven women of reproductive age with genital endometriosis were under observation. Treatment in the first group was carried out in accordance with the Guideline Development Group recommendations. Thirty-nine women of the second group additionally received a drug containing superoxide dismutase, resveratrol, and zinc. The control group included 30 healthy women. The state of lipid peroxidation processes was assessed by the level of diene conjugates and malondialdehyde in the blood serum and the antioxidant defense system by the content of superoxide dismutase and glutathione peroxidase. To monitor the patients’ quality of life, pain syndrome was studied using the Visual Analogue Scale. Statistical processing of the obtained data was carried out by means of the standard StatSoft Statistica for Windows 13.0 program pac­kage. Results. The assessment of the pain syndrome in the second group showed that it completely disappeared in women with the first stage of the disease. Among patients with the second stage, pain disappeared in 8 cases, 3 patients had a decrease from severe to mild pain. At the third stage, pain disappeared completely in 5 women, in 4 cases, it decreased from severe to mild, and in one woman, the pain decreased from unbearable to mild. All patients of the second group noted a decrease in pain during intercourse, and in the first stage — its absence, an increase in work capacity (r = 0.64, p &lt; 0.01), a decrease in irritability and anxiety in the perimenstrual period (r = –0.59, p &lt; 0.05) and overall satisfaction with the treatment result. Side effects were not noted in any of the patients. Conclusions. Improving treatment for genital endometriosis by supplementing therapy with superoxide dismutase, resveratrol, and zinc is pathogenetically justified, as it has a significant positive effect on the lipid peroxidation and antioxidant defense system, compared to the traditional treatment regimen.

A graph neural approach for group recommendation system based on pairwise preferences

Pairwise preference information, which involves users expressing their preferences by comparing items, plays a crucial role in decision-making and has recently found application in recommendation systems. In this study, we introduce GcPp, a clustering algorithm that leverages pairwise preference data to generate recommendations for user groups. Initially, we construct individual graphs for each user based on their pairwise preferences and utilize a graph convolutional network to predict similarities between all pairs of graphs. These predicted similarity scores form the foundation of our research. We then construct a new graph where users are nodes and the edges are weighted according to the predicted similarities. Finally, we perform clustering on the graph’s nodes (users). By evaluating various metrics, we found that employing a similarity metric based on a convolutional neural network (SimGNN) with our proposed ground truth called Top-K yielded the highest accuracy. The proposed approach is specifically designed for group recommendation systems and holds significant potential for group decision-making problems. Code is available at https://github.com/RozaAbolghasemi/Group_Recommendation_Syatem_GcPp_clustering.

An approach for explaining group recommendations based on negotiation information

Explaining group recommendations has gained importance over the last years. Although the topic of recommendation explanation has received attention in the context of single-user recommendations, only a few group recommender systems (GRS) currently provide explanations for their group recommendations. However, those GRS that support explanations, provide either explanations being highly reliant on the aggregation technique used for generating the recommendation (most of them trying to tackle shortcomings of the underlying technique), or explanations with a rich content but requiring users to provide considerable additional data. In this article, we present a novel approach for providing explanations of group recommendations, which are generated by a GRS based on multi-agent negotiation techniques. An evaluation of our approach with a user study in the movies domain has shown promising results. Explanations provided by our GRS system helped users during the decision-making process, since they modified the feedback given to recommended items. This is an improvement with respect to systems that do not provide explanations for their recommendations.

A Hierarchical Attention Network for Cross-Domain Group Recommendation.

Many online services allow users to participate in various group activities such as online meeting or group buying, and thus need to provide user groups with services that they are interested. The group recommender systems (GRSs) emerge as required and provide personalized services for various online user groups. Data sparsity is an important issue in GRSs, since even fewer group-item interactions are observed. Moreover, the group and the group members have complex and mutual relationships with each other, which exacerbates the difficulty in modeling the preferences of both a group and its members for recommendation. The cross-domain recommender system (CDRS) is a solution to alleviate data sparsity and assist preference modeling by transferring knowledge from a source domain which has relatively dense data to another. The existing CDRSs are usually developed for individual users and cannot be directly applied for group recommendation. To alleviate the data sparsity issue in GRSs, we first study the cross-domain group recommendation problem and propose a hierarchical attention network-based cross-domain group recommendation method, called HAN-CDGR. HAN-CDGR takes the advantage of data from a source domain to benefit recommendation generation for both the individual users and groups in the target domain which has data sparsity and cannot generate accurate recommendation. In HAN-CDGR, a hierarchical attention network is constructed to learn and model individual and group preferences, with consideration of both group members' interactions and dynamic weights and the complex relationships between individuals and groups. Adversarial learning is used to effectively transfer knowledge from a source domain to the target domain. Extensive experiments, which demonstrate the effectiveness and superiority of our proposal, providing accurate recommendation for both individual users and groups, are conducted on three tasks.

Operative management of osteochondral lesions of the talus: 2024 recommendations of the working group 'clinical tissue regeneration' of the German Society of Orthopedics and Traumatology (DGOU).

The working group 'Clinical Tissue Regeneration' of the German Society of Orthopedics and Traumatology (DGOU) issues this paper with updating its guidelines. Literature was analyzed regarding different topics relevant to osteochondral lesions of the talus (OLT) treatment. This process concluded with a statement for each topic reflecting the best scientific evidence available with a grade of recommendation. All group members rated the statements to identify possible gaps between literature and current clinical practice. Fixation of a vital bony fragment should be considered in large fragments. In children with open physis, retrograde drilling seems to work better than in adults, but even there, the revision rate reaches 50%. The literature supports debridement with bone marrow stimulation (BMS) in lesions smaller than 1.0 cm² without bony defect. The additional use of a scaffold can be recommended in lesions larger than 1.0 cm². For other scaffolds besides AMIC®/Chondro-Gide®, there is only limited evidence. Systematic reviews report good to excellent clinical results in 87% of the patients after osteochondral transplantation (OCT), but donor site morbidity is of concern, reaching 16.9%. There is no evidence of any additional benefit from autologous chondrocyte implantation (ACI). Minced cartilage lacks any supporting data. Metallic resurfacing of OLT can only be recommended as a second-line treatment. A medial malleolar osteotomy has a minor effect on the clinical outcome compared to the many other factors influencing the clinical result.

Enhancing group recommender systems: A fusion of social tagging and collaborative filtering for cohesive recommendations

AbstractThis study examines the challenges and opportunities of using group recommendation systems in an information overload scenario. Social network recommendation systems are increasingly important because they deliver users customized choices. Most existing solutions are geared for single users, making it difficult to propose for a group with different interests. This paper analyses group recommendation systems and exposes their flaws. This study tested whether the suggested approach outperforms the one without tagging information in recall, precision, and user satisfaction. Empirical evidence indicates that the algorithm exhibits appropriate levels of reliability and accuracy compared to conventional methods. The proposed approach has the potential to substantially enhance the existing state of social network group recommendation systems, thereby facilitating users in their quest to identify and participate in groups that align with their preferences.

Recommendations of Polish HCV Expert Group and Polish Society of Haematologists and Transfusiologists on diagnosis and treatment of HCV-infected hemato-oncology patients

Recommendations of Polish HCV Expert Group and Polish Society of Haematologists and Transfusiologists on diagnosis and treatment of HCV-infected hemato-oncology patients

Strategy for improving and empowering MSMEs through grouping using the AHC method

The high number of migrants in the city of Yogyakarta has resulted in increased opportunities for Micro, Small and Medium Enterprises (MSMEs) in Culinary and Handicrafts. The large amount of data collected by the Cooperative Office, which reached thousands, caused inas to have difficulties in determining what training was needed by MSMEs and also difficulties in choosing which MSMEs would receive training held by the Cooperative Office. In addition, the Yogyakarta Cooperatives and UMKM Office had difficulties in selecting which UMKM needed to receive these trainings. Grouping can be used as a strategy in selecting MSMEs and determining training according to their individual needs. The purpose of this study was to group SMEs using the Agglomerative Hierarchical Clustering Single Linkage method and its application to provide recommendations for MSME groups to the Yogyakarta Cooperative and MSME Office. The results of the recommendations for the number of groups can be used in providing implementation, design, and evaluation of the development and empowerment of MSME data in the City of Yogyakarta. This study uses the Agglomerative Hierarchical Clustering Single Linkage method. The stages in this research are Load Data, Cleaning Data, Data Selection, Transformation Data, Clustering Process with AHC single linkage, Silhouette Coefficient, and Knowledge Representation. This research resulted in 2 group recommendations from a total of 1336 Culinary MSME data and 3 group recommendations from a total of 145 Handicraft MSME data. The results of the silhouette score test in the Culinary Sector are included in the strong structure category with a value of 0.79 and the Crafts Sector is included in the Medium Structure category with a value of 0.615. From the number of these groups, recommendations were obtained for improving a service in increasing MSMEs, especially those with a turnover of less than 10 million, marketing purposes within the Yogyakarta area, and not having financial assistance from the government. The high number of immigrants in the city of Yogyakarta has resulted in increased opportunities for Micro, Small and Medium Enterprises (MSMEs) in the Culinary and Crafts sector. The large number of MSMEs creates increasingly higher competitiveness. Apart from that, the large amount of data collected by the Department of Cooperatives and MSMEs, which reaches thousands, causes the Department to have difficulties in efforts to improve and empower these MSMEs. Grouping is one method that can be used as a strategy in mapping MSMEs, especially in efforts to improve and empower MSMEs through training conducted by the Department. The aim of this research is to group MSMEs using the Agglomerative Hierarchical Clustering (AHC) method in an effort to achieve strategies for improving and empowering MSMEs. The focus of this research is[a1] MSMEs in the craft sector and MSMEs in the culinary sector. The results of this research provide 2 group recommendations from a total of 1336 Culinary MSME data and 3 group recommendations from a total of 145 Craft MSME data. The silhouette score test results in the Culinary Sector are in the strong structure category with a value of 0.79 and in the Crafts Sector are in the Medium Structure category with a value of 0.615. From the number of groups in the two MSMEs, strategies were obtained to improve and empower MSMEs, especially those with a turnover of less than 10 million, marketing objectives within the Yogyakarta area, and not having capital assistance from the government. [a1]the result of the revision of the Abstract

Incorporation of Two-Fold Trust in Group Recommender System to Handle Popularity Bias

Incorporation of Two-Fold Trust in Group Recommender System to Handle Popularity Bias

POI recommendation for random groups based on cooperative graph neural networks

Group Point-of-Interests (POI) recommendation devotes to find the optimal POIs for groups, which has extracted extensive attention. This work first brings forward a novel POI recommendation model for random groups based on Cooperative Graph Neural Networks (named as CGNN-PRRG). We have done three innovative work. (1) We propose a new fitted presentation learning method for generating the fitted representations of random groups. (2) To conquer the cold start issues in recommending POI for a new random group, we propose to take similar users’ (which have the similar representations with that of the random group) POI interaction data as the learning data. (3) We propose an Edge-learning enhanced Bipartite Graph Neural Network (EBGNN) to learn similar users’ POI comprehensive interaction preferences. Specially, EBGNN can learn the information on the edges of the graph. Meanwhile, we propose to learn similar users’ POI transfer preferences with the Session-based Graph Neural Networks (SRGNN). We verify our proposed model on the three public benchmark datasets (Foursquare, Gowalla and Yelp), which contain 124,933 to 860,888 POI check-in records. The comparison between our proposed model and ten representative baseline models demonstrates the outstanding performance of CGNN-PRRG. In terms of Precision@K and NDCG@K, our model achieves about 24.9% and 62.5% improvement compared with the best baseline models on the three benchmark datasets averagely. Adequate ablation experiments prove the effectiveness of the fitted representation generation method, similar users’ POI comprehensive interaction preferences learning method and the method for overcoming the cold start problem. The source code of the CGNN-PRRG model is available on github11https://github.com/IamMichaelMeng/CGNN_PRRG..

Vaccination acceptance and its associated factors in patients on hemodialysis in Austria: A nationwide survey.

Vaccines are essential in disease prevention among patients on chronic hemodialysis (HD). However, during the coronavirus disease 2019 pandemic, there has been an increased rate of vaccination hesitancy. A better understanding of patients' opinions may help identify a more targeted approach to increase vaccination rates. Questionnaires with 43 questions based on the recommendations of the Strategic Advisory Group of Experts (SAGE) on Immunization Working Group on Vaccine Hesitancy were administered to patients during routine HD sessions at different dialysis centers in Austria. In total, 347 patients participated in this study. Approximately 81% of the patients were aged > 54 years, and 65% were men. Further, 53% of patients were receiving HD from private units. In ~ 72% of patients, the dialysis physicians were the source of vaccination information. Meanwhile, the source of information in 28% of patients was the primary care physician (28%), and 18% of patients obtained vaccination details from the internet. The number of younger (aged < 55 years) patients who were more likely to use online content as the main source of information was significantly higher than that of older patients (32 vs. 15%, p = 0.001). Furthermore, the number of older patients who wanted to receive more information from the dialysis physician was significantly higher than that of younger patients (57 vs. 38%, p = 0.009). Only 65% of patients had a good understanding of the mechanisms of action of vaccines. The younger population (aged 18 - 54 years) had a higher number of individuals with a good understanding of vaccine mechanisms than the older population (78 vs. 62%, p = 0.016). Moreover, 86% of the whole population wanted to complete the recommended vaccinations. However, only 39% of respondents had sufficient information about the vaccination plan in Austrian. Numerous patients receiving HD wanted to obtain more information from their dialysis physicians. Increased awareness among providers and targeted communication might increase vaccination rates.

Aerobiological study in Lima, Perú. ¿Tipuana-Tipu, perhaps a new allergen?

To report the Tipuana tipu pollen as a new allergen capable of triggering allergic symptoms. The pollen counts were made according to standardized technique with a Burkard seven days following the European Aerobiology Society´s Network Group recommendations.1 The trap was installed on the roof of Clinica SANNA, El Golf, San Isidro, which is 20 m high, 12°5'54"S 77°3'6"W in the west-south of the Lima urban area. The sampling period was performed from September 2020 to October 2021. Collection of Tipuana tipu pollens and Preparation of Tipuana tipu pollen extracts 1:20 w/v was done using a previously described method.2 We carried out systematic skin prick testing with Tipuana tipu pollen extract and other aeroallergens (Dermatophagoides pteronyssinus, Dermatophagoides farinae, Blomia tropicalis), molds (Cladosporium herbarum, Alternaria alternata, Aspergillus fumigatus, Penicillium notatum), cat and dog danders, Periplaneta americana, grass six mix, weed mix (Inmunotek, Spain) on 80 patients (18 to 50 years old) seen in our allergy center, they suffering from november to january rhinitis and/or conjunctivitis symptoms. The majority living near avenues and large green areas, where Tipuana trees grew. We found a total of 952 grains/m3 of Tipuana tipu pollen between November 2020 to january 2021, with the maximum concentration of 37 grains/m3 on December 10th. We also found other airborne pollen Types: Poaceae, Myrtaceae, Compositae and Betulaceae. 14/80 patients (17,5%) showed positive skin prick test only to Tipuana tipu extract. Most of the patients with positive tests to Tipuana extract presented symptoms of rhinoconjunctivitis during the Tipuana pollination period. Four patients showed positive skin prick test to Tipuana tipu and grass 6 mix extracts, most of the rest of our patients were sensitized to dust mites' extracts (Dermatophagoides pteronyssinus). The west-south population of Lima urban city is exposed to Tipuana tipu pollen. We do not foud previous publications about Tipuana tipu allergy. Almost 18% of the patients tested in our sample were mono-sensitized to this pollen. The results of this study should be compared with data from the forthcoming years, to identify seasonal and annual fluctuations, extend the traps to other locations in Lima, and of course try to standardize and improve the Tipuana tipu pollen extract.

Using State Agency Reports to Augment Ohio’s Agricultural Injury Surveillance Efforts

ABSTRACT Background Agriculture is a hazardous industry with undocumented injury events. Credible surveillance measures are critical for this industry, especially to guide injury prevention programs with targeted recommendations for specific commodity groups and populations. This multi-phase study explored the feasibility for two state agency databases, the Ohio Bureau of Workers’ Compensation (BWC) Program and the Emergency Medical Services Incident Reporting System (EMSIRS), to augment the state’s Bureau of Labor Statistics (BLS) annual reports. Methods BWC data described injury claims in agricultural workplaces from 1999 to 2008. State EMSIRS data described the types of medical emergencies for which EMS services were requested to Ohio farms in 2013–2014. Descriptive analyses were performed on each distinctive source. Results Over 14,000 BWC claims were analyzed, with primary nature of injury identified as sprains and strains of bodily extremities; falls were the most common cause of injury. The EMSIRS data provided 1,376 cases, where EMS services were requested to Ohio farms at injury onset. Some cases had possibility to be excluded in CFOI or employment claims data, with 24% patients 65 years and older and 6% children 13 years and younger. The primary cause of injury was falls, and the highest reported injury type was blunt trauma. Conclusions Both BWC and EMSIRS databases showed the potential to enhance Ohio’s agricultural surveillance data with viable information not found in previously used systems. Each agency database had its own merits to further clarify and quantify morbidity. When used together, these sources enrich surveillance statistics to describe Ohio’s agricultural injury incidents.

Exploring content-based group recommendation for suggesting restaurants in Havana City

Recommender systems (RSs) are a relevant kind of artificial intelligence-based systems focused on providing users with the information that best fit their preferences and needs in a search space overloaded of possible options. Specifically, group recommender systems (GRSs) are a special type of RS centered on recommending items that are consumed in groups and not individually, being TV program and touristic packages key examples of such items. The current work is focused on proposing a content-based group recommendation approach (CB-GRS) contextualized to the restaurant recommendation domain. In contrast to previous content-based group recommendation models, the proposal incorporates novel stages such as restaurants feature imputation, the generation of a virtual group profile, the use of feature weighting, and the automatic selection of the most appropriate aggregation approach for composing group recommendations. The proposal is evaluated in an original recommendation scenario, related to restaurant from Havana City in Cuba, where several restaurant attributes are identified for applying the proposed CB-GRS approach. The experimental protocol evaluates individually each component of the proposal, evidencing their importance as part of the whole framework. Furthermore, the comparison with previous works has been also developed. The proposed approach can be applied in other recommendation scenarios, and in addition, the developed experimental protocol is generalizable for the evaluation of further content-based individual and group recommendation approaches in the tourism domain.