Historical Items Research Articles

Aggregating knowledge and collaborative information for sequential recommendation

Sequential recommendation aims to predict users’ future activities based on their historical interaction sequences. Various neural network architectures, such as Recurrent Neural Networks (RNN), Graph Neural Networks (GNN), and self-attention mechanisms, have been employed in the tasks, exploring multiple aspects of user preferences, including general interests, short-term interests, long-term interests, and item co-occurrence patterns. Despite achieving good performance, there are still limitations in capturing complex user preferences. Specifically, the current structures of RNN, GNN, etc., only capture item-level transition relations while neglecting attribute-level transition relations. Additionally, the explicit item relations are studied using item co-occurrence modules, but they cannot capture the implicit item-item relations. To address these issues, we propose a knowledge-augmented Gated Recurrent Unit (GRU) to improve the short-term user interest module and adopt a collaborative item aggregation method to enhance the item co-occurrence module. Additionally, our long-term interest module utilizes a bitwise gating mechanism to select historical item features significant to users’ current preferences. We extensively evaluate our model on three real-world datasets alongside competitive methods, demonstrating its effectiveness in top K sequential recommendation.

Disentangle interest trend and diversity for sequential recommendation

Based on historical behaviors, sequential recommendation endeavors to predict what a user prefers next. The recent efforts are mainly devoted to modeling the user’s interests evolution process or mining multi-interests for recommendation. However, it is largely overlooked that the interest trend (i.e., the evolution of the main interest) and the interest diversity (i.e., the scattered potential interests) could complement each other for better performance. Specifically, the interest trend reveals the user’s basic interest and its evolution, which is satisfied by similarity recommendations. Nevertheless, interest diversity covers the various interests caused by some external environmental influence, e.g., fashion trends and advertisements, exploring users’ potential interests or interest diversity will facilitate the model for diversity and serendipity recommendation. In a way, these two factors have conflicting aims, we argue that they should be disentangled in modeling first and recombined when making personalized recommendation.To instantiate this idea, we propose a simple yet effective model, dubbed Teddy (disentangles interest trend and diversity), which disentangles and then jointly models the aforementioned two factors under a unified framework. Particularly, in Teddy, an adaptive masking mechanism is first introduced to split the user’s historical items into two parts revealing her major interest trend and scattered interest diversity respectively for interests disentanglement. Then, a temporal convolutional network (TCN) is utilized to capture the evolution process of the user’s major interest trend. For the scattered interest diversity modeling, we further choose to apply Multilayer Perceptron (MLP) layers with max-pooling mechanism to extract the significant or dominant preference signals. The predicted scores generated by these two modules are aggregated together to integrate both interest trend and interest diversity for the final recommendation. Extensive experiments over four public datasets demonstrate the superiority of our proposed Teddy against a series of SOTA alternatives on the benchmark metrics.

Literary Associations in Rhyme Slang: Charles Dickens and His Characters in Rhyme Slang

The article aims at describing the literary associations of rhyming slang associated with the name of Charles Dickens, a classic of world literature, whose works were included in the treasury of both English and world literature and who became the most popular English-language writer during his lifetime, to reveal how the work of the eminent writer and unforgettable colorful characters, many of whom have become recognized types in English fiction, are represented in rhyming slang. The topic is examined using rhyming slang samples of containing the names of characters and titles of Charles Dickens's works, selected by a continuous sampling method from authoritative dictionaries of general and rhyming slang. Expressions of rhyming slang that refer to some important work of a writer or are based on the names of some significant characters are cultural items that are reflected in the collective memory of the British and are thus included in the so-called “current background knowledge” and “background knowledge of cultural heritage”. The rhymes contain precedent onyms and reflect the tendency to create new onomastic rhymes built on the names of famous and popular personalities from the world of cinema, pop music, show business, sports, politics, etc. Literary associations have not yet been the subject of special analysis and undoubtedly deserve linguistic and sociocultural description. The author's attention was drawn to the little-studied area, the analysis of which sets a new vector for the study of rhyming slang, which deals with cultural and historical items that are of certain value from the point of view of culture-oriented linguistics, cross-cultural communication and the general study of culture. The results of the study may be of use and interest to specialists developing topics in intercultural communication, linguocultural studies, contrastive linguistics of the English and Russian languages, foreign (English) literature, speech culture and in the practice of teaching English.

Editorial

The topic of repatriation has gained significant attention in recent years, particularly in relation to cultural artifacts and historical items. However, it is crucial to extend this conversation to include fossil specimens, which are important components of a nation’s natural and cultural heritages. Brazil – a country renowned for its rich biodiversity and geological significance – has an interest in ensuring the repatriation of its fossil specimens.Fossils hold immense scientific, cultural, and educational value. They provide invaluable insights into the Earth’s history, evolution of life forms, and climatic changes over millions of years. The fossil record of Brazil is particularly remarkable, containing specimens that are essential for understanding the evolutionary history of life in South America and in the broader global context.Despite their significance, many Brazilian fossils are housed in international institutions, private collections, and museums worldwide. The removal of these specimens from their country of origin often occurred during the colonial period or subsequently through acquisitions by foreigners. Despite some of these actions were undertaken with the intention of scientific study and preservation, it is crucial to acknowledge that repatriation is a matter of justice and sovereignty.Repatriating fossil specimens to their country of origin serves to multiple purposes. Firstly, it allows the countries to reclaim their natural heritage, reinforcing national identities and pride. It enables the scientific community within the country to have unrestricted access to these specimens, facilitating research and contributing to the advancement of knowledge in Paleontology and related fields. Furthermore, repatriation fosters the development of local expertise and encourages collaboration between researchers, strengthening scientific partnerships.Repatriation also promotes cultural exchange and educational opportunities. By showcasing these fossils in Brazilian museums and educational institutions, they become accessible to the public, providing a powerful tool for educating future generations about their natural heritage and the importance of conservation. The repatriated specimens can also serve as catalysts for tourism, attracting visitors from around the world to experience Brazil's unique geological and paleontological wonders firsthand.It is important to acknowledge the complexities involved in repatriation efforts. Collaboration and cooperation between governments, institutions, and researchers are crucial to establish effective processes for identifying, cataloging, and returning fossils. Transparency and respect for ethical guidelines should be central to these efforts, ensuring that repatriation is conducted responsibly and that the diligence is exercised to prevent the loss or damage of the specimens.In conclusion, the repatriation of fossil specimens to Brazil is a tool that aligns with principles of justice, national heritage, scientific advancement, and education. By reclaiming its natural treasures, Brazil can enrich its scientific and cultural scenario, while fostering international collaboration and understanding. It is incumbent upon the global community to support these efforts and recognize the significance of repatriation in preserving and celebrating the diverse natural heritage of nations worldwide.

3D Multispectral Imaging for Cultural Heritage Preservation: The Case Study of a Wooden Sculpture of the Museo Egizio di Torino

Digitalization techniques, such as photogrammetry (PG), are attracting the interest of experts in the cultural heritage field, as they enable the creation of three-dimensional virtual replicas of historical artifacts with 2D digital images. Indeed, PG allows for acquiring data regarding the overall appearance of an artifact, its geometry, and its texture. Furthermore, among several image-based techniques exploited for the conservation of works of art, multispectral imaging (MSI) finds great application in the study of the materials of historical items, taking advantage of the different responses of materials when exposed to specific wavelengths. Despite their great usefulness, PG and MSI are often used as separate tools. Integrating radiometric and geometrical data can notably expand the information carried by a 3D model. Therefore, this paper presents a novel research methodology that enables the acquisition of multispectral 3D models, combining the outcomes of PG and MSI (Visible (VIS), Ultraviolet-induced Visible Luminescence (UVL), Ultraviolet-Reflected (UVR), and Ultraviolet-Reflected False Color (UVR-FC) imaging) in a single coordinate system, using an affordable tunable set-up and open-source software. The approach has been employed for the study of two wooden artifacts from the Museo Egizio di Torino to investigate the materials present on the surface and provide information that could support the design of suitable conservation treatments.

FedGR: Federated Graph Neural Network for Recommendation Systems

Social recommendation systems based on the graph neural network (GNN) have received a lot of research-related attention recently because they can use social information to improve recommendation accuracy and because of the benefits derived from the excellent performance of the graph neural network in graphic data modeling. A large number of excellent studies in this area have been proposed one after another, but they all share a common requirement that the data should be centrally stored. In recent years, there have been growing concerns about data privacy. At the same time, the introduction of numerous stringent data protection regulations, represented by general data protection regulations (GDPR), has challenged the recommendation models with conventional centralized data storage. For the above reasons, we have designed a flexible model of recommendation algorithms for social scenarios based on federated learning. We call it the federated graph neural network for recommendation systems (FedGR). Previous related work in this area has only considered GNN, social networks, and federated learning separately. Our work is the first to consider all three together, and we have carried out a detailed design for each part. In FedGR, we used the graph attention network to assist in modeling the implicit vector representation learned by users from social relationship graphs and historical item graphs. In order to protect data privacy, we used FedGR flexible data privacy protection by incorporating traditional cryptography encryption techniques with the proposed “noise injection” strategy, which enables FedGR to ensure data privacy while minimizing the loss of recommended performance. We also demonstrate a different learning paradigm for the recommendation model under federation. Our proposed work has been validated on two publicly available popular datasets. According to the experimental results, FedGR has decreased MAE and RMSE compared with previous work, which proves its rationality and effectiveness.

MbSRS: A multi-behavior streaming recommender system

Streaming Recommender Systems (SRSs) have emerged to deliver recommendations based on pervasive data streams, which are a sequence of user-item interactions with multiple behavior types (e.g., purchase, add-to-cart, and view). However, existing SRSs all rely on a single behavior type (e.g., purchase) to make streaming recommendations, and commonly suffer from the data sparsity problem. To address this issue, the relatively more abundant multi-behavior interactions (i.e., interactions with multiple behavior types) could be well leveraged for more accurate streaming recommendations. However, it remains a challenge on how to effectively leverage the commonly-existing and complex multi-behavior interactions for improving the accuracy of streaming recommendations. Targeting at this challenge, we propose the first Multi-behavior Streaming Recommender System in the literature, called MbSRS, to elaborately exploit multi-behavior interactions for delivering accurate recommendations in streaming scenarios. In MbSRS, we first learn instant user preferences and unified item characteristics collaboratively from multi-behavior interactions. Then, we attentively learn long-term user preferences from the historical items interacted by the corresponding users. After that, we wisely fuse the learned instant and long-term user preferences via a gate mechanism. Finally, a novel multi-behavior-specific training process is devised for more effectively learning user preferences towards items from multi-behavior interactions. Extensive experiments on three real-world datasets demonstrate that the proposed MbSRS significantly outperforms the state-of-the-art baselines.

Day Seven

Day Seven Melissa Helton (bio) It’s been a week. And I don’t know what to say. It is so big. I can say it is three a.m. and my cat inexplicably woke me up at the same time that I stirred on July 28th, feeling queasy and uncomfortable enough that I sat up in bed in the dark, wondering if I needed a Tums, wondering if I was going to be sick, wondering why I felt so terrible. And then [End Page 78] I looked at my phone, which was silently blowing up with missed calls, texts, and messages. I did not go back to sleep. I can’t this morning either. I can give a record of events. How in the preceding days I had been in the joy of the forty-fifth annual Appalachian Writers’ Workshop, the first fully in-person workshop since the pandemic began. I had finished leading the Troublesome Team Trivia contest and driven home instead of staying on campus that night. So when the flood hit in the wee hours of that Thursday morning, I was able to act as remote communication, spending a literal eleven hours on my phone. I began relaying information across campus from an hour away since I had one contact with cell service in each of the four areas where the workshop writers were stranded by the flood water. Then arranging rides home for those whose cars had washed away or were four feet underwater, relaying road condition information, answering the concerns of writers not on campus. I can tell you how those eleven hours were filled with fear and then joy as I learned all my friends, teachers, mentors, and fellow writers were safe on and off campus, and managed to eventually make it home. I can talk about my first view of campus on Friday. The disorientation of book tables still set up for the remaining days of the writers’ workshop in one place, and broken glass, splintered wood, upended desks, and flood mud in others. The donations. The distribution. The crying community members who lost everything, or lost nothing and were heartbroken for others. The calls and texts and emails and social media posts and questions and best-guess decisions and donations and meals and stunned faces and hugs from strangers and mud and old photos and meals and water bottles and questions and questions and a few hours’ sleep at night to do it again for a week straight. [End Page 79] I can talk about being in charge of saving our archive. Ninety-five percent of the material was wet, seventy percent of it also covered in mud. Books, handwritten records, photos, quilts, baskets, files, silver nitrate negatives—precious historical items significant to us and the Appalachian region. I can describe standing there in the archive, my two teenagers sweeping the dark scene with flashlights as we sloshed through three-inch putrid mud, and how it was so big a disaster I didn’t know where to start, completely unqualified for such an important and time-sensitive task. And how that feeling has not gone away this entire week as we’ve hurried to do what we could. And the list of names and organizations who have emailed me advice, websites and tutorials, came on site for hours or days, helped pull materials from the molding rooms, helped make these sometimes educated and sometimes uneducated decisions, arranged for transport of documents or offered their freezer space for preservation—it’s a long list. If I began naming people and organizations, for each one I could pull forth here, I would forget at least six. Some names I never got in the first place. Our Great Hall became our supply distribution center and is also a working archive rescue center. Tables of diapers and garbage bags sit across from clotheslines of irreplaceable photos and slides slowly drying as folks hurry back and forth. And the only reason these items are being rescued is because of these volunteers. I can say how everyone has been thrust into positions where they are scrambling to learn what needs done and how to do it...

TRR: Target-relation regulated network for sequential recommendation.

Item co-occurrence is an important pattern in recommendation. Due to the difference in correlation, the matching degrees between the target and historical items vary. The higher the matching degree, the greater probability they co-occur. Recently, the recommendation performance has been greatly improved by leveraging item relations. As an important bond imposed by relations, these connected items should have a strong correlation in the calculation of certain measures. This kind of correlation can be the biased knowledge that benefits parameter training. Specifically, we focus on tuples containing the target item and latest relational items that have relations such as complement or substitute with the target item in user’s behavior sequence. Such close relations mean the matching degrees between relational items and historical items should be highly affected by that of the target item and historical items. For example, given a relational item having relation complement with the target item, if the target item has high matching degrees with some items in user’s behavior sequence, this complementary item should behave similarly for the co-occurrence of complementary items. Under guidance of the above thought, in this work, we propose a target-relation regulated mechanism which converts the biased knowledge of high correlation of matching degrees into a regulation. It integrates the target item and relational items in history as a whole to characterize the matching score between the target item and historical items. Experiments conducted on three real-world datasets demonstrate that our model can significantly outperform a set of state-of-the-art models.

Feature-Level Attentive ICF for Recommendation

Item-based collaborative filtering (ICF) enjoys the advantages of high recommendation accuracy and ease in online penalization and thus is favored by the industrial recommender systems. ICF recommends items to a target user based on their similarities to the previously interacted items of the user. Great progresses have been achieved for ICF in recent years by applying advanced machine learning techniques (e.g., deep neural networks) to learn the item similarity from data. The early methods simply treat all the historical items equally and recently proposed methods attempt to distinguish the different importance of historical items when recommending a target item. Despite the progress, we argue that those ICF models neglect the diverse intents of users on adopting items (e.g., watching a movie because of the director, leading actors, or the visual effects). As a result, they fail to estimate the item similarity on a finer-grained level to predict the user’s preference to an item, resulting in sub-optimal recommendation. In this work, we propose a general feature-level attention method for ICF models. The key of our method is to distinguish the importance of different factors when computing the item similarity for a prediction. To demonstrate the effectiveness of our method, we design a light attention neural network to integrate both item-level and feature-level attention for neural ICF models. It is model-agnostic and easy-to-implement. We apply it to two baseline ICF models and evaluate its effectiveness on six public datasets. Extensive experiments show the feature-level attention enhanced models consistently outperform their counterparts, demonstrating the potential of differentiating user intents on the feature-level for ICF recommendation models.

Attenuated and normalized item-item product network for sequential recommendation.

Sequential recommendation has become a research trending that exploits user’s recent behaviors for recommendation. The user-item interactions contain a sequential dependency that we need to capture to better recommend. Item-item Product (IIP), which models item co-occurrence, has shown good potential by characterizing the pairwise item relationships. Generally, recent behaviors have a greater impact on the current than long-term historical behaviors. And the decaying rate of influence around infrequent behaviors is fast. However, IIP ignores such a phenomenon when considering item-item relevance and leads to suboptimal performance. In this paper, we propose an attenuated IIP mechanism which is position-aware and decays the influence of historical items at an exponential rate. Besides, In order to make up for scenarios where the influence is not in a monotonous decline trend, we add another normalized IIP mechanism to complement the attenuated IIP mechanism. It also strengthen the model’s ability in discriminating favorite items under the sparse data condition by enlarging the gap of matching degree between items. Experiments conducted on five real-world datasets demonstrate that our proposed model achieves better performance than a set of state-of-the-art sequential recommendation models.

The history of the keyboard instrument MNP I 49 from the Museum of Musical Instruments in Poznań. the state of research

The keyboard instrument MNP I 49 from the Museum of Musical Instruments in Poznań has not been a subject of detailed academic studies yet, but there have been mentions of it in various types of publications throughout the years. The item is currently placed in the exhibition hall devoted to the art of the Baroque era in the Museum of Applied Arts in Poznań. It is a unique historical item in the Polish collection due to a very scarce number of harpsichords preserved in Poland. This situation is mainly a result of two world wars in the 20th century. Due to not enough available sources, the exact time of the creation of the instrument and the name of its builder were impossible to determine. The aim of the present article was to compile and arrange previous knowledge about the historical item MNP I 49. The work lists source materials and publications in which the instrument was mentioned, such as documents from the National Archive in Poznań, Raczyński Library in Poznań and National Museum Archive in Poznań. Based on the available source materials, the author was able to determine that the harpsichord appeared at the Skórzewski family’s palace in Czerniejewo before 1855.

Facadism: An Approach for Spatial Reconfiguration

Baghdad’s historical center is a rich site of heritage and cultural values, yet it suffers from urban deterioration. Many urban spaces and historical structures are aging, which has caused a decline in the vitality and function of axes and open spaces. This research is based on the principle of facadism as one of the main approaches to the preservation and rehabilitation of historic and traditional buildings. The purpose is to address urban degradation and the spatial reconfiguration of urban space in a way that promotes its sustainability and revitalization. This research aims to formulate a theoretical framework that includes a list of interference patterns and their role in spatial reconfiguration. This will be applied to the spatial reconfiguration and development of Al-Rasheed Street in the historic center of Baghdad. A questionnaire elicited the opinions of experts, designers, and implementers in academic and executive institutions on the possibility of reshaping local spaces using facadism. The results of the questionnaire showed that experts support the possibility of adopting this method in spatial reconfiguration in order to intervene in the degradation of historical environments, and also to create a homogeneous and interconnected urban environment that prevents the eradication of cultural and urban heritage. By adopting the preservation of a façade in its various forms, considerations need to be made regarding its compatibility with the nature of the problems in the study area and the ineffectiveness of the pattern of dismantling and transferring a building to another place. This is due to the importance of the historical place and the need to preserve all its historical items within the fabric, in addition to the effectiveness of some detailed patterns in different items of formation.

Is non-completion of treatment related to security need?

Treatment completion difficulties are common in forensic mental health settings and may have a profound impact on recidivism rates. To test for associations between measures of risk and of security needs on the one hand and treatment non-completion on the other among male offender-patients in one medium security hospital. We conducted a retrospective file study in a Flemish medium security hospital. A random sample of 25 treatment non-completers was compared to a random same-size sample of completers, each rated, blind to outcome, on the DUNDRUM-1 security needs scale from data recorded at the time of admission to the unit. 'Non-completion' was defined as any failure to complete treatment, whether staff-terminated or self-terminated; in Flanders, failure to comply with the judicial conditions of placement can result in re-imprisonment. We used binary logistic regression to test relationships between treatment completion/non-completion and security need, measured with the DUNDRUM-1, together with a range of possible confounding variables. Most patients had psychosis and/or personality disorder and often substance use disorders also. Treatment non-completion was invariably staff ordered because of security breaches. DUNDRUM-1 and PCL-R Facet 4 scores at the time of admission and HCR-20 scores during admission were significantly higher among non-completers than completers, but after binary logistic regression, only the DUNDRUM-1 rating was independently associated with non-completion. Our study showed that an admission DUNDRUM-1 rating, indicating levels of security need, co-varies only to a small extent with the historical items of the HCR-20, so may be regarded as measuring complementary domains. While conditions in Flanders at the time of the study complicated it in that medium security hospital units offered the highest level of hospital security available, the finding that non-completion of treatment was particularly likely when the DUNDRUM-1 indicated a higher security need than facilities could provide may have implications for all secure hospital services.

The influence of therapy alliance and treatment motivation in patients with Cluster B personality disorders on incidents in forensic hospitals

Purpose Nonspecific factors such as therapy alliance and treatment motivation have been shown to be predictive of therapy outcome. However, research investigating these factors among patients with personality disorders, or studies in the context of mandated treatment showed mixed results. A new theory furthermore speculates there may be differences between early formed therapeutic alliance (trait-like) versus alliance formed on the longer term (state-like). This paper aims to investigate the effects of therapy alliance and treatment motivation in 103 Dutch male forensic psychiatric patients with Cluster B personality disorders. Design/methodology/approach The authors used incidents as a measure of treatment outcome. They studied the effect of nonspecific factors on incidents in two phases, namely, 0 – 18 months and 18 – 36 months, along with known predictors of incidents (age, Historical items of the HCR-20 and psychopathy) as covariates. Findings Regression models predicting incidents in the first 18 months of treatment were nonsignificant. Incidents in the second 18 months were significantly predicted by models including alliance and motivation measured at the start of treatment, but not measures at 18 months and covariates. Predictors, except for age, were all nonsignificant. Practical implications These findings lend tentative support for the trait-like vs state-like theory of change through nonspecific factors. However, it may also be that other factors are more important in predicting therapy outcome in forensic psychiatric patients with Cluster B personality disorders. Originality/value The current study represents the first effort to study the effects of non-specific factors on therapeutic discourse in hospitalized offenders with Cluster B personality disorders.

American presidents and politicians in rhyming slang

The article is aimed at identifying onomastic rhymes as part of rhyming slang and analyzing them from a socio-cultural perspective. They are built on the names of American celebrities from the world of politics and social activities and believed to be fixers of cultural and historical items that are of certain value from the point of view of culture-oriented linguistics, cross-cultural communication and the general study of culture. TThe research methods applied are determined by the purpose and objectives of the research and include a descriptive and a linguistic ones, the latter comprising context and definitional analysis, and also semantic interpretation. The rhymes are based on the names that have been widely represented in the media from the middle of the twentieth century to the present day, thus forming part of the modern cultural collective memory of the carriers of the English-speaking culture. The noted tendency of preferential creation of new rhymes, exploiting precedent onyms, became dominant in the development of rhyming slang at the turn of the century. The authors come to the conclusion that the rhymes illustrating the world of high politics have been added to the well-mastered and familiar onomastic rhymes, built on the names of celebrities from the world of cinema, pop music, popular culture and sports. The article brings to light the rhymes that have not yet been recorded in authoritative slang dictionaries. The research results can be of interest to the specialists working on the topics of intercultural communication, linguistic and cultural studies, cultural linguistics, political linguistics, euphemization, contrastive linguistics of the English and Russian languages.

Toward Dynamic User Intention

User intention is an important factor to be considered for recommender systems, which always changes dynamically in different contexts. Recent studies (represented by sequential recommendation) begin to focus on predicting what users want beyond what users like, which are better at capturing user intention and have attracted a surge of interest. However, user intention modeling is non-trivial, because it is generally influenced by various factors, among which item relations and their temporal evolutionary effects are of great importance. For example, consumption of a cellphone will have varying impacts on the demands for its relational items: For complements, the demands are likely to be promoted in the short term; while for substitutes, the long-term effect may take advantage, because users do not need another cellphone immediately. Moreover, the temporal evolutions of different relational effects vary across different domains, which makes it challenging to adaptively take them into consideration. As a result, most existing studies only loosely incorporate item relations by encoding their semantics into embeddings, neglecting fine-grained time-aware effects. In this work, we propose Knowledge-aware Dynamic Attention (KDA) to take both relational effects and their temporal evolutions into consideration. Specifically, to model dynamic impacts of historical relational interactions on user intention, we aggregate the history sequence into relation-specific embeddings, where the attention weight consists of two parts. First, we measure the relational intensity between historical items and the target item to model the absolute degree of influence in terms of each relation. Second, to model how the relational effects drift with time, we innovatively introduce Fourier transform with learnable frequency-domain embeddings to estimate temporal decay functions of different relations adaptively. Subsequently, the self-attention mechanism is leveraged to derive the final representation of the whole history sequence, which reflects the dynamic user intention and will be applied to generate the recommendation list. Extensive experiments in three real-world datasets indicate the proposed KDA model significantly outperforms the state-of-the-art methods on the Top- K recommendation task. Moreover, the proposed Fourier-based method opens up a new avenue to adaptively integrate temporal dynamics into general neural models.

Cultures of Two Worlds: Štefka Cobelj’s Contribution to the Establishment of Museum Collections in Slovenia and Somalia

Slovenian Štefka Cobelj (1923–1989) saw her work of an art historian and ethnologist as a calling, and dedicated her life entirely to it. She specialized in Baroque and Yugoslavian and international contemporary art, but was most passionate about world ethnology. As the director of the Ptuj museum in Slovenia, and later a museum consultant in Mogadishu in Somalia, she was involved in the creation of ethnology collections of national importance. On her numerous travels for both business and pleasure, she compiled a large personal collection of cultural, historical, and ethnological items. This article describes her contribution to the creation of collections in Ptuj and Mogadishu, and her personal heritage, which was bequeathed to the following Slovenian institutions: Celje Regional Museum, Maribor Art Gallery, Maribor Regional Museum, Ivan Potrč Library Ptuj, and Ptuj-Ormož Regional Museum.

Lead in plastics – Recycling of legacy material and appropriateness of current regulations

X-ray fluorescence spectrometry has been employed to measure Pb in a wide range of consumer and environmental plastics, including food-packaging material, household goods, electronic casings, beach litter and agricultural waste. Results reveal high concentrations of Pb (>1000 mg kg−1) in historical items that are still in use or circulation (e.g. toys, construction plastics, wiring insulation) and variable, but generally lower concentrations in more recently manufactured articles. Analysis of Br, Cl and Cr, proxies for brominated flame retardants, polyvinyl chloride (PVC) and chromate pigments, respectively, suggests that as historical material is recycled, Pb from electronic plastics and pigments, but not PVC, is dispersed into a variety of newer products. Although most cases in the consumer sector comply with relevant EU Directives, some products that are non-compliant highlight shortfalls in regulations where recycling is involved and potential problems arising from the direct fashioning of industrial plastics into new consumer goods through attempts to be environmentally positive. The uncontrolled loss of historical and recycled plastics has also resulted in Pb contamination of the environment. Here, it is proposed that litter can be classified as hazardous depending on its Pb content and according to existing regulations that embrace consumer plastics.

British state, public and political figures of the late 20th - early 21st century in rhyming slang

The article aims at providing an adequate linguistic and sociocultural description of rhyming slang based on the use of the names of prominent British government and public figures and politicians, who were widely represented in the British media at the turn of the 20th and 21st centuries, and are thus included in modern cultural collective memory of the carriers of the English lingual culture. The rhymes contain precedents of onyms − the personal names of well-known, fashionable, popular, or scandalous politicians. The noted tendency of the preferred creation of new rhymes, exploiting the precedent onyms, has become dominant in the development of rhyming slang at the turn of the century. The emergence of rhyming slang units based on the use of the precedent names of politicians and statesmen is a relatively new and insufficiently studied phenomenon while onomastic rhymes that exploit the names of celebrities from the world of cinema, pop music, popular culture and sports are more common and are better studied. The article contains the rhymes that have not yet been recorded in authoritative slang dictionaries. They surely deserve linguistic and sociocultural descriptions.The authors focused on a special and research-promising layer of vocabulary that reflects the sociocultural and historical items in the context of the so-called cultural literacy and is of certain value from the point of view of culture-oriented linguistics, cross-cultural communication and the general study of culture.The results of the research can be useful and interesting for specialists who develop topics of cross-cultural communication, culture-oriented linguistics, linguistic culturology, euphemy, contrastive linguistics of the English and Russian languages.