The condition assessment of underground infrastructure (UI) is critical for maintaining the safety, functionality, and longevity of subsurface assets like tunnels and pipelines. This article reviews various data acquisition techniques, comparing their strengths and limitations in UI condition assessment. In collecting structured data, traditional methods like strain gauge can only obtain relatively low volumes of data due to low sampling frequency, manual data collection, and transmission, whereas more advanced and automatic methods like distributed fiber optic sensing can gather relatively larger volumes of data due to automatic data collection, continuous sampling, or comprehensive monitoring. Upon comparison, unstructured data acquisition methods can provide more detailed visual information that complements structured data. Methods like closed-circuit television and unmanned aerial vehicle produce large volumes of data due to their continuous video recording and high-resolution imaging, posing great challenges to data storage, transmission, and processing, while ground penetration radar and infrared thermography produce smaller volumes of image data that are more manageable. The acquisition of large volumes of UI data is the first step in its condition assessment. To enable more efficient, accurate, and reliable assessment, it is recommended to (1) integrate data analytics like artificial intelligence to automate the analysis and interpretation of collected data, (2) to develop robust big data management platforms capable of handling large volumes of data storage, processing and analysis, (3) to couple different data acquisition technologies to leverage the strengths of each technique, and (4) to continuously improve data acquisition methods to ensure efficient and reliable data acquisition.

Scholars studying organizations often work with multiple datasets lacking shared identifiers or covariates. In such situations, researchers usually use approximate string (“fuzzy”) matching methods to combine datasets. String matching, although useful, faces fundamental challenges. Even where two strings appear similar to humans, fuzzy matching often struggles because it fails to adapt to the informativeness of the character combinations. In response, a number of machine learning methods have been developed to refine string matching. Yet, the effectiveness of these methods is limited by the size and diversity of training data. This paper introduces data from a prominent employment networking site (LinkedIn) as a massive training corpus to address these limitations. By leveraging information from the LinkedIn corpus regarding organizational name-to-name links, we incorporate trillions of name pair examples into various methods to enhance existing matching benchmarks and performance by explicitly maximizing match probabilities. We also show how relationships between organization names can be modeled using a network representation of the LinkedIn data. In illustrative merging tasks involving lobbying firms, we document improvements when using the LinkedIn corpus in matching calibration and make all data and methods open source.

Unstructured data are a promising new source of information that insurance companies may use to understand their risk portfolio better and improve the customer experience. However, these novel data sources are difficult to incorporate into existing ratemaking frameworks due to the size and format of the unstructured data. This paper proposes a framework to use street view imagery within a generalized linear model. To do so, we use representation learning to extract an embedding vector containing useful information from the image. This embedding is dense and low dimensional, making it appropriate to use within existing ratemaking models. We find that there is useful information included in street view imagery to predict the frequency of claims for certain types of perils. This model can be used as in a ratemaking framework but also opens the door to future empirical research on attempting to extract which characteristics within the image leads to increased or decreased predicted claim frequencies. Throughout, we discuss the practical difficulties (technical and social) of using this type of data for insurance pricing.

This article introduces to political science a framework to analyze the content of visual material through unsupervised and semi-supervised methods. It details the implementation of a tool from the computer vision field, the Bag of Visual Words (BoVW), for the definition and extraction of “tokens” that allow researchers to build an Image-Visual Word Matrix which emulates the Document-Term matrix in text analysis. This reduction technique is the basis for several tools familiar to social scientists, such as topic models, that permit exploratory, and semi-supervised analysis of images. The framework has gains in transparency, interpretability, and inclusion of domain knowledge with respect to other deep learning techniques. I illustrate the scope of the BoVW by conducting a novel visual structural topic model which focuses substantively on the identification of visual frames from the pictures of the migrant caravan from Central America.

This article is an analysis of linguistic survey data representing German dialects in Switzerland in 1933/34 based on the so-called Wenker sentences. The data are impressionistic in terms of applied phonetic transcriptions, which were produced by non-specialists using the Latin alphabet. Due to the lack of pre-defined standardization, the phonetic transcriptions are very heterogeneous. From a technical perspective, this leads to very noisy data, which is why the validity of the Wenker data in general and the Swiss Wenker data in particular has been questioned. Using methods from computational linguistics, we compare, for the first time, Wenker data with linguistic data collected at virtually the same time by linguistics professionals. Direct comparison with a sample from the published atlas of German-speaking Switzerland (SDS) reveals that despite the noisiness of the data, they nevertheless provide reliable information, e.g., in terms of the spatial structuring of Swiss dialects. The study is thus a successful pilot for other corpus-based studies dealing with unstructured Wenker data in other regions.