BONNIE: Building Online Narratives from Noteworthy Interaction Events

Nowadays, we have access to data of unprecedented volume, high dimensionality, and complexity. To extract novel insights from such complex and dynamic data, we need effective and efficient strategies. One such strategy is to combine data analysis and visualization techniques, which are the essence of visual analytics applications. After the knowledge discovery process, a major challenge is to filter the essential information that has led to a discovery and to communicate the findings to other people, explaining the decisions they may have made based on the data. We propose to record and use the trace left by the exploratory data analysis, in the form of user interaction history, to aid this process. With the trace, users can choose the desired interaction steps and create a narrative, sharing the acquired knowledge with readers. To achieve our goal, we have developed the BONNIE ( Building Online Narratives from Noteworthy Interaction Events ) framework. BONNIE comprises a log model to register the interaction events, auxiliary code to help developers instrument their own code, and an environment to view users’ own interaction history and build narratives. This article presents our proposal for communicating discoveries in visual analytics applications, the BONNIE framework, and the studies we conducted to evaluate our solution. After two user studies (the first one focused on history visualization and the second one focused on narrative creation), our solution has showed to be promising, with mostly positive feedback and results from a Technology Acceptance Model ( TAM ) questionnaire.

A Knowledge Graph-Enhanced Attention Aggregation Network for Making Recommendations

In recent years, many researchers have devoted time to designing algorithms used to introduce external information from knowledge graphs, to solve the problems of data sparseness and the cold start, and thus improve the performance of recommendation systems. Inspired by these studies, we proposed KANR, a knowledge graph-enhanced attention aggregation network for making recommendations. This is an end-to-end deep learning model using knowledge graph embedding to enhance the attention aggregation network for making recommendations. It consists of three main parts. The first is the attention aggregation network, which collect the user’s interaction history and captures the user’s preference for each item. The second is the knowledge graph-embedded model, which aims to integrate the knowledge. The semantic information of the nodes and edges in the graph is mapped to the low-dimensional vector space. The final part is the information interaction unit, which is used for fusing the features of two vectors. Experiments showed that our model achieved a stable improvement compared to the baseline model in making recommendations for movies, books, and music.

Limited Scope for Group Coordination in Stylistic Variations of Kolam Art

In large, complex societies, assorting with others with similar social norms or behaviors can facilitate successful coordination and cooperation. The ability to recognize others with shared norms or behaviors is thus assumed to be under selection. As a medium of communication, human art might reflect fitness-relevant information on shared norms and behaviors of other individuals thus facilitating successful coordination and cooperation. Distinctive styles or patterns of artistic design could signify migration history, different groups with a shared interaction history due to spatial proximity, as well as individual-level expertise and preferences. In addition, cultural boundaries may be even more pronounced in a highly diverse and socially stratified society. In the current study, we focus on a large corpus of an artistic tradition called kolam that is produced by women from Tamil Nadu in South India (N = 3, 139 kolam drawings from 192 women) to test whether stylistic variations in art can be mapped onto caste boundaries, migration and neighborhoods. Since the kolam art system with its sequential drawing decisions can be described by a Markov process, we characterize variation in styles of art due to different facets of an artist's identity and the group affiliations, via hierarchical Bayesian statistical models. Our results reveal that stylistic variations in kolam art only weakly map onto caste boundaries, neighborhoods, and regional origin. In fact, stylistic variations or patterns in art are dominated by artist-level variation and artist expertise. Our results illustrate that although art can be a medium of communication, it is not necessarily marked by group affiliation. Rather, artistic behavior in this context seems to be primarily a behavioral domain within which individuals carve out a unique niche for themselves to differentiate themselves from others. Our findings inform discussions on the evolutionary role of art for group coordination by encouraging researchers to use systematic methods to measure the mapping between specific objects or styles onto groups.

An embedded bandit algorithm based on agent evolution for cold-start problem

Purpose Many recommender systems are generally unable to provide accurate recommendations to users with limited interaction history, which is known as the cold-start problem. This issue can be resolved by trivial approaches that select random items or the most popular one to recommend to the new users. However, these methods perform poorly in many cases. This paper aims to explore the problem that how to make accurate recommendations for the new users in cold-start scenarios. Design/methodology/approach In this paper, the authors propose embedded-bandit method, inspired by Word2Vec technique and contextual bandit algorithm. The authors describe user contextual information with item embedding features constructed by Word2Vec. In addition, based on the intelligence measurement model in Crowd Science, the authors propose a new evaluation method to measure the utility of recommendations. Findings The authors introduce Word2Vec technique for constructing user contextual features, which improved the accuracy of recommendations compared to traditional multi-armed bandit problem. Apart from this, using this study’s intelligence measurement model, the utility also outperforms. Practical implications Improving the accuracy of recommendations during the cold-start phase can greatly raise user stickiness and increase user favorability, which in turn contributes to the commercialization of the app. Originality/value The algorithm proposed in this paper reflects that user contextual features can be represented by clicked items embedding vector.

Improving Sequential Recommendation Consistency with Self-Supervised Imitation

Most sequential recommendation models capture the features of consecutive items in a user-item interaction history. Though effective, their representation expressiveness is still hindered by the sparse learning signals. As a result, the sequential recommender is prone to make inconsistent predictions. In this paper, we propose a model, SSI, to improve sequential recommendation consistency with Self-Supervised Imitation. Precisely, we extract the consistency knowledge by utilizing three self-supervised pre-training tasks, where temporal consistency and persona consistency capture user-interaction dynamics in terms of the chronological order and persona sensitivities, respectively. Furthermore, to provide the model with a global perspective, global session consistency is introduced by maximizing the mutual information among global and local interaction sequences. Finally, to comprehensively take advantage of all three independent aspects of consistency-enhanced knowledge, we establish an integrated imitation learning framework. The consistency knowledge is effectively internalized and transferred to the student model by imitating the conventional prediction logit as well as the consistency-enhanced item representations. In addition, the flexible self-supervised imitation framework can also benefit other student recommenders. Experiments on four real-world datasets show that SSI effectively outperforms the state-of-the-art sequential recommendation methods.

Stellar substructures in the periphery of the magellanic clouds with the VISTA hemisphere survey from the red clump and other tracers

We study the morphology of the stellar periphery of the Magellanic Clouds in search of substructure using near–infrared imaging data from the VISTA Hemisphere Survey (VHS). Based on the selection of different stellar populations using the (J − Ks, Ks) colour–magnitude diagram, we confirm the presence of substructures related to the interaction history of the Clouds and find new substructures on the eastern side of the LMC disc which may be owing to the influence of the Milky Way, and on the northern side of the SMC, which is probably associated to the ellipsoidal structure of the galaxy. We also study the luminosity function of red clump stars in the SMC and confirm the presence of a bi–modal distance distribution, in the form of a foreground population. We find that this bi–modality is still detectable in the eastern regions of the galaxy out to a 10○ distance from its centre. Additionally, a background structure is detected in the North between 7○ and 10○ from the centre which might belong to the Counter Bridge, and a foreground structure is detected in the South between 6○ and 8○ from the centre which might be linked to the Old Bridge.

Interactions, information and emergence: Exploring task allocation in ant colonies using network analysis

In animal societies, individuals may take on different roles to fulfil their own needs and the needs of their groups. Ant colonies display high levels of organisational complexity, with ants fulfilling different roles at different timescales (what is known as task allocation). Factors affecting task allocation can be at the individual level (e.g., physiology), or at the group level (e.g., interaction histories). In this work, we focus on group level processes by exploring the impact of the history of interaction networks on task allocation and task switching using a previously published dataset (Mersch et al., 2013) tracking the behaviour of six Camponotus fellah colonies over 41 days. First, we investigated the architecture of interaction networks using node (individual) level network measures and their relation to the individual's task - foraging, cleaning or nursing - and whether or not the ant switched tasks. We then explored how noisy information propagation is among ants, as a function of the colony composition (how many ants are carrying out which tasks), through the information-theoretic metric of effective information. Our results show that interaction history affected task allocation, with ants more likely to switch to a task if they had interacted with other ants carrying out that task. The degree to which interaction history affected task allocation, as well as the noise in their interactions, depended on which groups of ants are interacting. Overall, we showed that colony cohesion is stable even as ant-level network measures vary more for ants when they switched functional groups; thus ant colonies maintain a high level of information flow as determined by network analysis and ant functional groups play different roles in maintaining colony cohesion.

Introduction to Matrix Factorization for Recommender Systems

Recommender systems aim to personalize the experience of user by suggesting items to the user based on the preferences of a user. The preferences are learned from the user’s interaction history or through explicit ratings that the user has given to the items. The system could be part of a retail website, an online bookstore, a movie rental service or an online education portal and so on. In this paper, I will focus on matrix factorization algorithms as applied to recommender systems and discuss the singular value decomposition, gradient descent-based matrix factorization and parallelizing matrix factorization for large scale applications.

A review of recommendation system research based on bipartite graph

The interaction history between users and items is usually stored and displayed in the form of bipartite graphs. Neural network recommendation based on the user-item bipartite graph has a significant effect on alleviating the long-standing data sparseness and cold start of the recommendation system. The whole paper is based on the bipartite graph. An review of the recommendation system of graphs summarizes the three characteristics of graph neural network processing bipartite graph data in the recommendation field: interchangeability, Multi-hop transportability, and strong interpretability. The biggest contribution of the full paper is that it summarizes the general framework of graph neural network processing bipartite graph recommendation from the models with the best recommendation effect in the past three years: embedding layer, propagation update layer, and prediction layer. Although there are subtle differences between different models, they are all this framework can be applied, and different models can be regarded as variants of this general model, that is, other models are fine-tuned on the basis of this framework. At the end of the paper, the latest research progress is introduced, and the main challenges and research priorities that will be faced in the future are pointed out.