Steffen Pielström

Bio: Steffen Pielström is an academic researcher from University of Würzburg. The author has contributed to research in topics: Stylometry & Digging. The author has an hindex of 5, co-authored 12 publications receiving 179 citations.

Understanding and explaining Delta measures for authorship attribution

Abstract: This article builds on a mathematical explanation of one the most prominent stylometric measures, Burrows’s Delta (and its variants), to understand and explain its working. Starting with the conceptual separation between feature selection, feature scaling, and distance measures, we have designed a series of controlled experiments in which we used the kind of feature scaling (various types of standardization and normalization) and the type of distance measures (notably Manhattan, Euclidean, and Cosine) as independent variables and the correct authorship attributions as the dependent variable indicative of the performance of each of the methods proposed. In this way, we are able to describe in some detail how each of these two variables interact with each other and how they influence the results. Thus we can show that feature vector normalization, that is, the transformation of the feature vectors to a uniform length of 1 (implicit in the cosine measure), is the decisive factor for the improvement of Delta proposed recently. We are also able to show that the information particularly relevant to the identification of the author of a text lies in the profile of deviation across the most frequent words rather than in the extent of the deviation or in the deviation of specific words only. .................................................................................................................................................................................

Sequential Soil Transport and Its Influence on the Spatial Organisation of Collective Digging in Leaf-Cutting Ants

Abstract: The Chaco leaf-cutting ant Atta vollenweideri (Forel) inhabits large and deep subterranean nests composed of a large number of fungus and refuse chambers. The ants dispose of the excavated soil by forming small pellets that are carried to the surface. For ants in general, the organisation of underground soil transport during nest building remains completely unknown. In the laboratory, we investigated how soil pellets are formed and transported, and whether their occurrence influences the spatial organisation of collective digging. Similar to leaf transport, we discovered size matching between soil pellet mass and carrier mass. Workers observed while digging excavated pellets at a rate of 26 per hour. Each excavator deposited its pellets in an individual cluster, independently of the preferred deposition sites of other excavators. Soil pellets were transported sequentially over 2 m, and the transport involved up to 12 workers belonging to three functionally distinct groups: excavators, several short-distance carriers that dropped the collected pellets after a few centimetres, and long-distance, last carriers that reached the final deposition site. When initiating a new excavation, the proportion of long-distance carriers increased from 18% to 45% within the first five hours, and remained unchanged over more than 20 hours. Accumulated, freshly-excavated pellets significantly influenced the workers' decision where to start digging in a choice experiment. Thus, pellets temporarily accumulated as a result of their sequential transport provide cues that spatially organise collective nest excavation.

Soil Moisture and Excavation Behaviour in the Chaco Leaf-Cutting Ant (Atta vollenweideri): Digging Performance and Prevention of Water Inflow into the Nest

Abstract: The Chaco leaf-cutting ant Atta vollenweideri is native to the clay-heavy soils of the Gran Chaco region in South America. Because of seasonal floods, colonies are regularly exposed to varying moisture across the soil profile, a factor that not only strongly influences workers' digging performance during nest building, but also determines the suitability of the soil for the rearing of the colony's symbiotic fungus. In this study, we investigated the effects of varying soil moisture on behaviours associated with underground nest building in A. vollenweideri. This was done in a series of laboratory experiments using standardised, plastic clay-water mixtures with gravimetric water contents ranging from relatively brittle material to mixtures close to the liquid limit. Our experiments showed that preference and group-level digging rate increased with increasing water content, but then dropped considerably for extremely moist materials. The production of vibrational recruitment signals during digging showed, on the contrary, a slightly negative linear correlation with soil moisture. Workers formed and carried clay pellets at higher rates in moist clay, even at the highest water content tested. Hence, their weak preference and low group-level excavation rate observed for that mixture cannot be explained by any inability to work with the material. More likely, extremely high moistures may indicate locations unsuitable for nest building. To test this hypothesis, we simulated a situation in which workers excavated an upward tunnel below accumulated surface water. The ants stopped digging about 12 mm below the interface soil/water, a behaviour representing a possible adaptation to the threat of water inflow field colonies are exposed to while digging under seasonally flooded soils. Possible roles of soil water in the temporal and spatial pattern of nest growth are discussed.

Towards a better understanding of Burrows's Delta in literary authorship attribution

Abstract: Burrows’s Delta is the most established measure for stylometric difference in literary authorship attribution. Several improvements on the original Delta have been proposed. However, a recent empirical study showed that none of the proposed variants constitute a major improvement in terms of authorship attribution performance. With this paper, we try to improve our understanding of how and why these text distance measures work for authorship attribution. We evaluate the effects of standardization and vector normalization on the statistical distributions of features and the resulting text clustering quality. Furthermore, we explore supervised selection of discriminant words as a procedure for further improving authorship attribution.

Hybrid context enriched deep learning model for fine-grained sentiment analysis in textual and visual semiotic modality social data

Abstract: Detecting sentiments in natural language is tricky even for humans, making its automated detection more complicated. This research proffers a hybrid deep learning model for fine-grained sentiment prediction in real-time multimodal data. It reinforces the strengths of deep learning nets in combination to machine learning to deal with two specific semiotic systems, namely the textual (written text) and visual (still images) and their combination within the online content using decision level multimodal fusion. The proposed contextual ConvNet-SVMBoVW model, has four modules, namely, the discretization, text analytics, image analytics, and decision module. The input to the model is multimodal text, m e {text, image, info-graphic}. The discretization module uses Google Lens to separate the text from the image, which is then processed as discrete entities and sent to the respective text analytics and image analytics modules. Text analytics module determines the sentiment using a hybrid of a convolution neural network (ConvNet) enriched with the contextual semantics of SentiCircle. An aggregation scheme is introduced to compute the hybrid polarity. A support vector machine (SVM) classifier trained using bag-of-visual-words (BoVW) for predicting the visual content sentiment. A Boolean decision module with a logical OR operation is augmented to the architecture which validates and categorizes the output on the basis of five fine-grained sentiment categories (truth values), namely ‘highly positive,’ ‘positive,’ ‘neutral,’ ‘negative’ and ‘highly negative.’ The accuracy achieved by the proposed model is nearly 91% which is an improvement over the accuracy obtained by the text and image modules individually.

Authenticating the writings of Julius Caesar

Abstract: We shed new light on the authenticity of the writings of Julius Caesar.Hirtius, one of Caesar's generals, must have contributed to Caesar's writings.We benchmark two authorship verification systems on publicly available data sets.We test on both modern data sets, and Latin texts from Antiquity.We show how computational methods inform traditional authentication studies. In this paper, we shed new light on the authenticity of the Corpus Caesarianum, a group of five commentaries describing the campaigns of Julius Caesar (100-44 BC), the founder of the Roman empire. While Caesar himself has authored at least part of these commentaries, the authorship of the rest of the texts remains a puzzle that has persisted for nineteen centuries. In particular, the role of Caesar's general Aulus Hirtius, who has claimed a role in shaping the corpus, has remained in contention. Determining the authorship of documents is an increasingly important authentication problem in information and computer science, with valuable applications, ranging from the domain of art history to counter-terrorism research. We describe two state-of-the-art authorship verification systems and benchmark them on 6 present-day evaluation corpora, as well as a Latin benchmark dataset. Regarding Caesar's writings, our analyses allow us to establish that Hirtius's claims to part of the corpus must be considered legitimate. We thus demonstrate how computational methods constitute a valuable methodological complement to traditional, expert-based approaches to document authentication.

Cooperative transport in ants: a review of proximate mechanisms

Abstract: The behavioral mechanisms that lead to cooperation in social insects are often unknown or poorly understood. Cooperative transport, or the movement of an object by two or more individuals, is a particularly impressive example of collaboration among workers. Many ant species perform this behavior, but there is extreme interspecific variation in efficiency. Why are some ant species so efficient at cooperative transport, while others are so inefficient? Surprisingly, the scientific community has little proximate understanding of the adaptations that make certain species excel at this behavior. This work provides a review of the behavioral rules that separate the efficient cooperative transporters from the inefficient. We present two measures of efficiency of cooperative transport as well as a flowchart of the cooperative transport process. By identifying the steps and flow of information, the flowchart enables careful modeling of cooperative transport from a mechanistic perspective. Previous studies of each of the four phases of cooperative transport are discussed, including decision, recruitment, organization, and transport. We also present hypotheses regarding behavioral mechanisms that may modulate efficiency.

When social behaviour is moulded in clay: on growth and form of social insect nests

Abstract: The nests built by social insects are among the most complex structures produced by animal groups. They reveal the social behaviour of a colony and as such they potentially allow comparative studies. However, for a long time, research on nest architecture was hindered by the lack of technical tools allowing the visualisation of their complex 3D structures and the quantification of their properties. Several techniques, developed over the years, now make it possible to study the organisation of these nests and how they are built. Here, we review present knowledge of the mechanisms of nest construction, and how nest structure affects the behaviour of individual insects and the organisation of activities within a colony.

Authorship Attribution for Neural Text Generation

Abstract: In recent years, the task of generating realistic short and long texts have made tremendous advancements. In particular, several recently proposed neural network-based language models have demonstrated their astonishing capabilities to generate texts that are challenging to distinguish from human-written texts with the naked eye. Despite many benefits and utilities of such neural methods, in some applications, being able to tell the “author” of a text in question becomes critically important. In this work, in the context of this Turing Test, we investigate the so-called authorship attribution problem in three versions: (1) given two texts T1 and T2, are both generated by the same method or not? (2) is the given text T written by a human or machine? (3) given a text T and k candidate neural methods, can we single out the method (among k alternatives) that generated T? Against one humanwritten and eight machine-generated texts (i.e., CTRL, GPT, GPT2, GROVER, XLM, XLNET, PPLM, FAIR), we empirically experiment with the performance of various models in three problems. By and large, we find that most generators still generate texts significantly different from human-written ones, thereby making three problems easier to solve. However, the qualities of texts generated by GPT2, GROVER, and FAIR are better, often confusing machine classifiers in solving three problems. All codes and datasets of our experiments are available at: https://bit.ly/ 302zWdz