Online Museums Segmentation with Structured Data: The Case of the Canary Island’s Online Marketplace

This paper’s primary objective is to segment the online marketplace of the Canary Islands’ museums by using different conversion funnel metrics. Little systematic research exists on digital user behaviour, and much less is known about how to segment cultural users with structured data from manually extracted and SEO software sources. With this aim in mind, we built a database with data related to the different phases of the conversion funnel of the museums to segment this online museum marketplace. In the findings, not only do we acknowledge the existence of different segments, but we also provide insight into the user’s digital behaviour by considering different metrics from the different phases of the conversion model process (awareness, consideration, conversion and loyalty). The originality of this paper is multifold. Firstly, it estimates the potential optimisation of these websites to improve the digital marketing implemented by the museum sector of the Canary Islands. Secondly, it sheds light on what benchmarking tactics and statistics procedures can be followed to carry out a non-hierarchical segmentation with standardised and comparable data. Thirdly, it contributes to the literature of digital marketing by eclectically combining the conversion funnel model, benchmarking techniques and non-hierarchical segmentation procedures.

Narrative event segmentation in the cortical reservoir

Recent research has revealed that during continuous perception of movies or stories, humans display cortical activity patterns that reveal hierarchical segmentation of event structure. Thus, sensory areas like auditory cortex display high frequency segmentation related to the stimulus, while semantic areas like posterior middle cortex display a lower frequency segmentation related to transitions between events. These hierarchical levels of segmentation are associated with different time constants for processing. Likewise, when two groups of participants heard the same sentence in a narrative, preceded by different contexts, neural responses for the groups were initially different and then gradually aligned. The time constant for alignment followed the segmentation hierarchy: sensory cortices aligned most quickly, followed by mid-level regions, while some higher-order cortical regions took more than 10 seconds to align. These hierarchical segmentation phenomena can be considered in the context of processing related to comprehension. In a recently described model of discourse comprehension word meanings are modeled by a language model pre-trained on a billion word corpus. During discourse comprehension, word meanings are continuously integrated in a recurrent cortical network. The model demonstrates novel discourse and inference processing, in part because of two fundamental characteristics: real-world event semantics are represented in the word embeddings, and these are integrated in a reservoir network which has an inherent gradient of functional time constants due to the recurrent connections. Here we demonstrate how this model displays hierarchical narrative event segmentation properties beyond the embeddings alone, or their linear integration. The reservoir produces activation patterns that are segmented by a hidden Markov model (HMM) in a manner that is comparable to that of humans. Context construction displays a continuum of time constants across reservoir neuron subsets, while context forgetting has a fixed time constant across these subsets. Importantly, virtual areas formed by subgroups of reservoir neurons with faster time constants segmented with shorter events, while those with longer time constants preferred longer events. This neurocomputational recurrent neural network simulates narrative event processing as revealed by the fMRI event segmentation algorithm provides a novel explanation of the asymmetry in narrative forgetting and construction. The model extends the characterization of online integration processes in discourse to more extended narrative, and demonstrates how reservoir computing provides a useful model of cortical processing of narrative structure.

Exploring the Intensity of Relationships with Vocational Education Centres: A Typology of Spanish SMEs

Even though the availability of skilled labour and technological know-how is critical to the sustainability of small and medium-sized enterprises (SMEs), the relationships between industry and the vocational education system have received little attention in the recent literature regarding social aspects of innovation. The objective of this paper is to analyse the intensity of relationships between industrial SMEs and vocational education and training (VET) centres from the firms’ perspective. The study is based on a survey carried out with a sample of 1388 Spanish industrial SMEs with vocational education graduates among their employees. Multivariate hierarchical segmentation techniques were used in order to identify the main explanatory variables. As a result, we obtained a typology (“tree”) of eight organizational profiles associated to different intensity levels (from higher to lower) of relationships between firms and schools. The results show that most industrial SMEs maintain relations with vocational education centres, reflecting the importance of the latter for the companies. The organisational type having the highest level of relations refers to SMEs with experience in external cooperation (cooperation with other actors in innovation projects) which have vocational education employees (graduates) in technical areas and which are bigger in size. Likewise, the results suggest that fruitful collaboration between SMEs and vocational education centres depends on the existence of an established culture of innovation among the smaller firms. This work sheds light on economic and social sustainability. Its results and discussion are linked to the objectives of United Nations sustainable development goals and the recent communication from the European Commission to the European Parliament entitled “European skills agenda for sustainable competitiveness, social fairness, and resilience”.

Walking on broken glass: gender as predictor of job precariousness among young people in Spain

Previous evidence reveals that socioeconomic factors, such as contract duration, occupation, activity sector, age, training, nationality, marital status or gender, lead to precariousness. This research looks into the intersectionality of inequalities in order to explain the impact of precariousness among young people based on gender. Data from the Spanish Labor Force Survey (EPA) from 2005 to 2016 has been analyzed using logistic regression and hierarchical segmentation. Results suggest that the economic crisis has widened the gender gap in precarious jobs, such that currently, young women are more likely to face precarious situations as compared to young men.

Narrative Event Segmentation in the Cortical Reservoir

During continuous perception of movies or stories, awake humans display cortical activity patterns that reveal hierarchical segmentation of event structure. Sensory areas like auditory cortex display high frequency segmentation related to the stimulus, while semantic areas like posterior middle cortex display a lower frequency segmentation related to transitions between events (Baldassano et al. 2017). These hierarchical levels of segmentation are associated with different time constants for processing. Chien and Honey (2020) observed that when two groups of participants heard the same sentence in a narrative, preceded by different contexts, neural responses for the groups were initially different and then gradually aligned. The time constant for alignment followed the segmentation hierarchy: sensory cortices aligned most quickly, followed by mid-level regions, while some higher-order cortical regions took more than 10 seconds to align. These hierarchical segmentation phenomena can be considered in the context of processing related to comprehension. Uchida et al. (2021) recently described a model of discourse comprehension where word meanings are modeled by a language model pre-trained on a billion word corpus (Yamada et al 2020). During discourse comprehension, word meanings are continuously integrated in a recurrent cortical network. The model demonstrates novel discourse and inference processing, in part because of two fundamental characteristics: real-world event semantics are represented in the word embeddings, and these are integrated in a reservoir network which has an inherent gradient of functional time constants due to the recurrent connections. Here we demonstrate how this model displays hierarchical narrative event segmentation properties. The reservoir produces activation patterns that are segmented by the HMM of Baldassano et al (2017) in a manner that is comparable to that of humans. Context construction displays a continuum of time constants across reservoir neuron subset, while context forgetting has a fixed time constant across these subsets. Virtual areas formed by subgroups of reservoir neurons with faster time constants segmented with shorter events, while those with longer time constants preferred longer events. This neurocomputational recurrent neural network simulates narrative event processing as revealed by the fMRI event segmentation algorithm of Baldassano et al (2017), and provides a novel explanation of the asymmetry in narrative forgetting and construction observed by Chien and Honey (2020). The model extends the characterization of online integration processes in discourse to more extended narrative, and demonstrates how reservoir computing provides a useful model of cortical processing of narrative structure.

Analysis of segmentation ontology reveals the similarities and differences in connectivity onto L2/3 neurons in mouse V1

Quantitatively comparing brain-wide connectivity of different types of neuron is of vital importance in understanding the function of the mammalian cortex. Here we have designed an analytical approach to examine and compare datasets from hierarchical segmentation ontologies, and applied it to long-range presynaptic connectivity onto excitatory and inhibitory neurons, mainly located in layer 2/3 (L2/3), of mouse primary visual cortex (V1). We find that the origins of long-range connections onto these two general cell classes—as well as their proportions—are quite similar, in contrast to the inputs on to a cell type in L6. These anatomical data suggest that distal inputs received by the general excitatory and inhibitory classes of neuron in L2/3 overlap considerably.

Identification and Evaluation of Urban Construction Waste with VHR Remote Sensing Using Multi-Feature Analysis and a Hierarchical Segmentation Method

With rapid urbanization, the disposal and management of urban construction waste have become the main concerns of urban management. The distribution of urban construction waste is characterized by its wide range, irregularity, and ease of confusion with the surrounding ground objects, such as bare soil, buildings, and vegetation. Therefore, it is difficult to extract and identify information related to urban construction waste by using the traditional single spectral feature analysis method due to the problem of spectral confusion between construction waste and the surrounding ground objects, especially in the context of very-high-resolution (VHR) remote sensing images. Considering the multi-feature analysis method for VHR remote sensing images, we propose an optimal method that combines morphological indexing and hierarchical segmentation to extract the information on urban construction waste in VHR images. By comparing the differences between construction waste and the surrounding ground objects in terms of the spectrum, geometry, texture, and other features, we selected an optimal feature subset to improve the separability of the construction waste and other objects; then, we established a classification model of knowledge rules to achieve the rapid and accurate extraction of construction waste information. We also chose two experimental areas of Beijing to validate our algorithm. By using construction waste separability quality evaluation indexes, the identification accuracy of construction waste in the two study areas was determined to be 96.6% and 96.2%, the separability indexes of the construction waste and buildings reached 1.000, and the separability indexes of the construction waste and vegetation reached 1.000 and 0.818. The experimental results show that our method can accurately identify the exposed construction waste and construction waste covered with a dust screen, and it can effectively solve the problem of spectral confusion between the construction waste and the bare soil, buildings, and vegetation.