A Comparative Performance Study of Classification Models for Opinion Mining

Opinion mining has become a major part in today's economy. People would want to know more about a product and the customers opinion before buying it. Companies would also want to know the opinions of the customers. Therefore, analyzing the customer’s opinion is important. A new customer would consider a product as good by analyzing the opinions of other customers. The opinions are collected from various areas, which include blogs, web forums, and product review sites. Classifying these large set of opinions requires a good classifier. In view of this, a comparative study of three classification techniques - Naive Bayes classifier with Kernel Density Estimation (KDE), Support Vector Machine (SVM), Decision Tree and KNN was made. To evaluate the classifier accuracy, precision, recall and F-measure techniques are used. Experimental results show that the Naive Bayes with Kernel Density Estimation (KDE) classifier achieved higher accuracy among others.

Detecting and Visualizing Observation Hot-Spots in Massive Volunteer-Contributed Geographic Data across Spatial Scales Using GPU-Accelerated Kernel Density Estimation

Volunteer-contributed geographic data (VGI) is an important source of geospatial big data that support research and applications. A major concern on VGI data quality is that the underlying observation processes are inherently biased. Detecting observation hot-spots thus helps better understand the bias. Enabled by the parallel kernel density estimation (KDE) computational tool that can run on multiple GPUs (graphics processing units), this study conducted point pattern analyses on tens of millions of iNaturalist observations to detect and visualize volunteers’ observation hot-spots across spatial scales. It was achieved by setting varying KDE bandwidths in accordance with the spatial scales at which hot-spots are to be detected. The succession of estimated density surfaces were then rendered at a sequence of map scales for visual detection of hot-spots. This study offers an effective geovisualization scheme for hierarchically detecting hot-spots in massive VGI datasets, which is useful for understanding the pattern-shaping drivers that operate at multiple spatial scales. This research exemplifies a computational tool that is supported by high-performance computing and capable of efficiently detecting and visualizing multi-scale hot-spots in geospatial big data and contributes to expanding the toolbox for geospatial big data analytics.

Estimating the Gait Speed of Older Adults in Smart Home Environments

Mobility is one of the key performance indicators of the health condition of older adults. One important parameter is the gait speed. The mobility is usually assessed under the supervision of a professional by standardised geriatric assessments. Using sensors in smart home environments for continuous monitoring of the gait speed enables physicians to detect early stages of functional decline and to initiate appropriate interventions. This in combination with a floor plan smart home sensors were used to calculate the distance that a person walked in the apartment and the inertial measurement unit data for estimating the actual walking time. A Gaussian kernel density estimator was applied to the computed values and the maximum of the kernel density estimator was considered as the gait speed. The proposed method was evaluated on a real-world dataset and the estimations of the gait speed had a deviation smaller than $$0.10 \, \frac{\mathrm{m}}{\mathrm{s}}$$ 0.10 m s , which is smaller than the minimal clinically important difference, compared to a baseline from a standardised geriatrics assessment.

Ranging Patterns and Site Fidelity of Snubfin Dolphins in Yawuru Nagulagun/Roebuck Bay, Western Australia

For long-lived species such as marine mammals, having sufficient data on ranging patterns and space use in a timescale suitable for population management and conservation can be difficult. Yawuru Nagulagun/Roebuck Bay in the northwest of Western Australia supports one of the largest known populations of Australian snubfin dolphins (Orcaella heinsohni)—a species with a limited distribution, vulnerable conservation status, and high cultural value. Understanding the species’ use of this area will inform management for the long-term conservation of this species. We combined 11 years of data collected from a variety of sources between 2007 and 2020 to assess the ranging patterns and site fidelity of this population. Ranging patterns were estimated using minimum convex polygons (MCPs) and fixed kernel densities (weighted to account for survey effort) to estimate core and representative areas of use for both the population and for individuals. We estimated the population to range over a small area within the bay (103.05 km2). The Mean individual representative area of use (95% Kernel density contour) was estimated as 39.88 km2 (± 32.65 SD) and the Mean individual core area of use (50% Kernel density contour) was estimated as 21.66 km2 (±18.85 SD) with the majority of sightings located in the northern part of the bay less than 10 km from the coastline. Most individuals (56%) showed moderate to high levels of site fidelity (i.e., part-time or long-term residency) when individual re-sight rates were classified using agglomerative hierarchical clustering (AHC). These results emphasize the importance of the area to this vulnerable species, particularly the area within the Port of Broome that has been identified within the population’s core range. The pressures associated with coastal development and exposure to vessel traffic, noise, and humans will need to be considered in ongoing management efforts. Analyzing datasets from multiple studies and across time could be beneficial for threatened species where little is known on their ranging patterns and site fidelity. Combined datasets can provide larger sample sizes over an extended period of time, fill knowledge gaps, highlight data limitations, and identify future research needs to be considered with dedicated studies.