The authorship of questioned documents often constitutes important evidence in criminal and civil cases. Linguistic stylistic analysis can often help to determine authorship. Computational methods have been applied to authorship analysis in academia for decades, and in recent years have achieved the levels of reliability needed for application to real-world cases. This article surveys the different types of computational authorship analysis methods and their components in a practical vein—describing the assumptions each makes, the analytic controls they require, and the tests needed to measure and ensure their reliability. Specifically, I discuss many of the potential pitfalls in their application, to guide practitioners in more effectively achieving trustworthy and understandable results. It must always be remembered, though, that there is no substitute for expertise, experience, and careful human judgment.

In response to recommendations to redefine statistical significance to P ≤ 0.005, we propose that researchers should transparently report and justify all choices they make when designing a study, including the alpha level.

This book constitutes the proceedings of the First International Conference on Big Data Computing and Communications, BigCom 2015, held in Taiyuan, China, in August 2015. The 41 papers presented in th

Style is a fundamental and ubiquitous aspect of the human experience: Everyone instantly and constantly assesses people and things according to their individual styles, academics establish careers by researching musical, artistic, or architectural styles, and entire industries maintain themselves by continuously creating and marketing new styles. Yet what exactly style is and how it works are elusive: We certainly know it when we see it, but there is no shared and clear understanding of the diverse phenomena that we call style. The Structure of Style explores this issue from a computational viewpoint, in terms of how information is represented, organized, and transformed in the production and perception of different styles. New computational techniques are now making it possible to model the role of style in the creation of and response to human artifactsand therefore to develop software systems that directly make use of style in useful ways. Argamon, Burns, and Dubnov organize the research they have collected in this book according to the three roles that computation can play in stylistics. The first section of the book, Production, provides conceptual foundations by describing computer systems that create artifactsmusical pieces, texts, artworksin different styles. The second section, Perception, explains methods for analyzing different styles and gleaning useful information, viewing style as a form of communication. The final section, Interaction, deals with reciprocal interaction between style producers and perceivers, in areas such as interactive media, improvised musical accompaniment, and game playing. The Structure of Style is written for researchers and practitioners in areas including information retrieval, computer art and music, digital humanities, computational linguistics, and artificial intelligence, who can all benefit from this comprehensive overview and in-depth description of current research in this active interdisciplinary field.

True natural language understanding requires the ability to identify and understand metaphorical utterances, which are ubiquitous in human communication of all kinds. At present, however, even the problem of identifying metaphors in arbitrary text is very much an unsolved problem, let alone analyzing their meaning. Furthermore, no current methods can be transferred to new languages without the development of extensive language-specific knowledge bases and similar semantic resources. In this paper, we present a new language-independent ensemble-based approach to identifying linguistic metaphors in natural language text. The system's architecture runs multiple corpus-based metaphor identification algorithms in parallel and combines their results. The architecture allows easy integration of new metaphor identification schemes as they are developed. This new approach achieves state-of-the-art results over multiple languages and represents a significant improvement over existing methods for this problem.

Full natural language understanding requires identifying and analyzing the meanings of metaphors, which are ubiquitous in both text and speech. Over the last thirty years, linguistic metaphors have been shown to be based on more general conceptual metaphors, partial semantic mappings between disparate conceptual domains. Though some achievements have been made in identifying linguistic metaphors over the last decade or so, little work has been done to date on automatically identifying conceptual metaphors. This paper describes research on identifying conceptual metaphors based on corpus data. Our method uses as little background knowledge as possible, to ease transfer to new languages and to mini- mize any bias introduced by the knowledge base construction process. The method relies on general heuristics for identifying linguistic metaphors and statistical clustering (guided by Wordnet) to form conceptual metaphor candidates. Human experiments show the system effectively finds meaningful conceptual metaphors.

ii Introduction Characteristic to all areas of human activity (from poetic to ordinary to scientific) and, thus, to all types of discourse, metaphor becomes an important problem for natural language processing. Its ubiquity in language has been established in a number of corpus studies and the role it plays in human reasoning has been confirmed in psychological experiments. This makes metaphor an important research area for computational and cognitive linguistics, and its automatic identification and interpretation indispensable for any semantics-oriented NLP application. The work on metaphor in NLP and AI started in the 1980s, providing us with a wealth of ideas on the structure and mechanisms of the phenomenon. The last decade witnessed a technological leap in natural language computation, whereby manually crafted rules gradually give way to more robust corpus-based statistical methods. This is also the case for metaphor research. In the recent years, the problem of metaphor modeling has been steadily gaining interest within the NLP community, with a growing number of approaches exploiting statistical techniques. Compared to more traditional approaches based on hand-coded knowledge, these more recent methods tend to have a wider coverage, as well as be more efficient, accurate and robust. However, even the statistical metaphor processing approaches so far often focused on a limited domain or a subset of phenomena. At the same time, recent work on computational lexical semantics and lexical acquisition techniques, as well as a wide range of NLP methods applying machine learning to open-domain semantic tasks, open many new avenues for creation of large-scale robust tools for recognition and interpretation of metaphor. This workshop is the first one focused on modelling of metaphor using NLP techniques. Recent related events include workshops on Computational Approaches to Figurative Language (NAACL 2007) and on Computational Approaches to Linguistic Creativity (NAACL 2009, NAACL 2010). We received 14 submissions and accepted 10. Each paper was carefully reviewed by at least 3 members of the Program Committee. The selected papers offer explorations into the following directions: (1) creation of metaphor-annotated datasets; (2) identification of new features that are useful for metaphor identification; (3) cross-lingual metaphor identification. The papers represent a variety of approaches to utilization and creation of datasets. While existing annotated corpora were used in some papers (Dunn, Tsvetkov et al), most papers describe creation of new annotated materials. Along with annotation guidelines adapted from the MIP and MIPVU procedures (Badryzlova et al), more intuitive …

This paper considers four versions of the authorship attribution problem that are typically encountered in the forensic context and offers algorithmic solutions for each. Part I describes the simple authorship attribution problem described above. Part II considers the long-text verification problem, in which we are asked if two long texts are by the same author. Part III discusses the many-candidates problem, in which we are asked which among thousands of candidate authors is the author of a given text. Finally, Part IV considers the fundamental problem of authorship attribution, in which we are asked if two short texts are by the same author. Although other researchers have considered these problems, here we offer our own solutions to each problem and indicate the degree of accuracy that can be expected in each case under specified conditions.

Much of the past work in structured sentiment extraction has been evaluated in ways that summarize the output of a sentiment extraction technique for a particular application. In order to get a true picture of how accurate a sentiment extraction system is, however, it is important to see how well it performs at finding individual mentions of opinions in a corpus. Past work also focuses heavily on mining opinion/product-feature pairs from product review corpora, which has lead to sentiment extraction systems assuming that the documents they operate on are review-like — that each document concerns only one topic, that there are lots of reviews on a particular product, and that the product features of interest are frequently recurring phrases. Based on existing linguistics research, this dissertation introduces the concept of an appraisal expression, the basic grammatical unit by which an opinion is expressed about a target. The IIT sentiment corpus, intended to present an alternative to both of these assumptions that have pervaded structured sentiment analysis research, consists of blog posts annotated with appraisal expressions to enable the evaluation of how well sentiment analysis systems find individual appraisal expressions. This dissertation introduces FLAG, an automated system for extracting appraisal expressions. FLAG operates based on a three step process: (1) identifying attitude groups using a lexicon-based shallow parser, (2) identifying potential structures for the rest of the appraisal expression by identifying patterns in a sentence's dependency parse tree, (3) selecting the best appraisal expression for each attitude group using a discriminative reranker. FLAG achieves an overall accuracy of 0.261 F1 at correctly identifying appraisal expressions, which is good considering the difficulty of the task.

Most previous work on authorship attribution has focused on the case in which we need to attribute an anonymous document to one of a small set of candidate authors. In this paper, we consider authorship attribution as found in the wild: the set of known candidates is extremely large (possibly many thousands) and might not even include the actual author. Moreover, the known texts and the anonymous texts might be of limited length. We show that even in these difficult cases, we can use similarity-based methods along with multiple randomized feature sets to achieve high precision. Moreover, we show the precise relationship between attribution precision and four parameters: the size of the candidate set, the quantity of known-text by the candidates, the length of the anonymous text and a certain robustness score associated with a attribution.

A central concern in Evidence Based Medicine (EBM) is how to convey research results effectively to practitioners. One important idea is to summarize results by key summary statistics that describe the effectiveness (or lack thereof) of a given intervention, specifically the absolute risk reduction (ARR) and number needed to treat (NNT). Manual summarization is slow and expensive, thus, with the exponential growth of the biomedical research literature, automated solutions are needed. In this paper, we present a novel method for automatically creating EBM-oriented summaries from research abstracts of randomly-controlled trials (RCTs). The system extracts descriptions of the treatment groups and outcomes, as well as various associated quantities, and then calculates summary statistics. Results on a hand-annotated corpus of research abstracts show promising, and potentially useful, results.

The computational analysis of the style of natural language texts, computational stylistics, seeks to develop automated methods to (1) effectively distinguish texts with one stylistic character from those of another, and (2) give a meaningful representation of the differences between textual styles. Such methods have many potential applications in areas including criminal and national security forensics, customer relations management, spam/scam filtering, and scholarly research. In this chapter, we propose a framework for research in computational stylistics, based on a functional model of the communicative act. We illustrate the utility of this framework via several case studies.

Accurate and relevant intelligence is critical for effective counterterrorism. Too much irrelevant information is as bad or worse than not enough information. Modern computational tools promise to provide better search and summarization capabilities to help analysts filter and select relevant and key information. However, to do this task effectively, such tools must have access to levels of meaning beyond the literal. Terrorists operating in context-rich cultures like fundamentalist Islam use messages with multiple levels of interpretation, which are easily misunderstood by non-insiders. This chapter discusses several kinds of such "encryption" used by terrorists and insurgents in the Arabic language, and how knowledge of such methods can be used to enhance computational text analysis techniques for use in counterterrorism.

ImagIne that you have been gIven an Important text of unknown authorship, and wish to know as much as possible about the unknown author (demographics, personality, cultural background, among others), just by analyzing the given text. This authorship profiling problem is of growing importance in the current global information environment– applications abound in forensics, security, and commercial settings. For example, authorship profiling can help police identify characteristics of the perpetrator of a crime when there are too few (or too many) specific suspects to consider. Similarly, large corporations may be interested in knowing what types of people like or dislike their products, based on analysis of blogs and online product reviews. The question we therefore ask is: How much can we discern about the author of a text simply by analyzing the text itself? It turns out that, with varying degrees of accuracy, we can say a great deal indeed. Unlike the problem of authorship attribution (determining the author of a text from a given candidate set) discussed recently in these pages by Li, Zheng, and Chen authorship profiling does not begin with a set of writing samples from known candidate authors. Instead, we exploit the sociolinguistic observation that different groups of people speaking or writing in a particular genre and in a particular language use that language differently. That is, they vary in how often they use certain words or syntactic constructions (in addition to variation in pronunciation or intonation, for example). The particular profile dimensions we consider here are author gender, age,8 native language7 and personality.10

Modern terrorist networks pose an unprecedented threat to international security. The question of how to neutralize that threat is complicated radically by their fluid, non-hierarchical structures, religious and ideological motivations, and predominantly non-territorial objectives. Governments and militaries are crafting new policies and doctrines to combat terror, but they desperately need new technologies to make these efforts effective. This book collects a wide range of the most current computational research that addresses critical issues for countering terrorism, including: Finding, summarizing, and evaluating relevant information from large and changing data stores; Simulating and predicting enemy acts and outcomes; and Producing actionable intelligence by finding meaningful patterns hidden in huge amounts of noisy data. The books four sections describe current research on discovering relevant information buried in vast amounts of unstructured data; extracting meaningful information from digitized documents in multiple languages; analyzing graphs and networks to shed light on adversaries goals and intentions; and developing software systems that enable analysts to model, simulate, and predict the effects of real-world conflicts. The research described in this book is invaluable reading for governmental decision-makers designing new policies to counter terrorist threats, for members of the military, intelligence, and law enforcement communities devising counterterrorism strategies, and for researchers developing more effective methods for knowledge discovery in complicated and diverse datasets.

Recently, philosophers of science have argued that the epistemological requirements of different scientific fields lead necessarily to differences in scientific method. In this paper, we examine possible variation in how language is used in peer-reviewed journal articles from various fields to see if features of such variation may help to elucidate and support claims of methodological variation among the sciences. We hypothesize that significant methodological differences will be reflected in related differences in scientists' language style.This paper reports a corpus-based study of peer-reviewed articles from twelve separate journals in six fields of experimental and historical sciences. Machine learning methods were applied to compare the discourse styles of articles in different fields, based on easily-extracted linguistic features of the text. Features included function word frequencies, as used often in computational stylistics, as well as lexical features based on systemic functional linguistics, which affords rich resources for comparative textual analysis. We found that indeed the style of writing in the historical sciences is readily distinguishable from that of the experimental sciences. Furthermore, the most significant linguistic features of these distinctive styles are directly related to the methodological differences posited by philosophers of science between historical and experimental sciences, lending empirical weight to their contentions.

In this paper, we address a relatively new and interesting text categorization problem: classify a political blog as either liberal or conservative, based on its political leaning. Our subjectivity analysis based method is twofold: 1) we identify subjective sentences that contain at least two strong subjective clues based on the General Inquirer dictionary; 2) from subjective sentences identified, we extract opinion expressions and other features to build political leaning classifiers. Experimental results with a political blog corpus we built show that by using features from subjective sentences can significantly improve the classification performance. In addition, by extracting opinion expressions from subjective sentences, we are able to reveal opinions that are characteristic of a specific political leaning to some extent.

Sentiment analysis seeks to characterize opinionated or evaluative aspects of natural language text. We suggest here that appraisal expression extraction should be viewed as a fundamental task in sentiment analysis. An appraisal expression is a textual unit expressing an evaluative stance towards some target. The task is to find and characterize the evaluative attributes of such elements. This paper describes a system for effectively extracting and disambiguating adjectival appraisal expressions in English outputting a generic representation in terms of their evaluative function in the text. Data mining on appraisal expressions gives meaningful and non-obvious insights.

Most text analysis and retrieval work to date has focused on the topic of a text; that is, what it is about. However, a text also contains much useful information in its style, or how it is written. This includes information about its author, its purpose, feelings it is meant to evoke, and more. This article develops a new type of lexical feature for use in stylistic text classification, based on taxonomies of various semantic functions of certain choice words or phrases. We demonstrate the usefulness of such features for the stylistic text classification tasks of determining author identity and nationality, the gender of literary characters, a text's sentiment (positive/negative evaluation), and the rhetorical character of scientific journal articles. We further show how the use of functional features aids in gaining insight about stylistic differences among different kinds of texts.

Much interesting text n the web consists largely of opinionated or evaluative text, as opposed to directly informative text. The new field of 'sentiment analysis' seeks to characterize such aspects of natural language text, as opposed to just the bare facts. We suggest that 'appraisal expression extraction' should be viewed as a fundamental task for sentiment analysis. We define an 'appraisal expression' to be a piece of text expressing some evaluative stance towards a particular object. The task is to find these elements and characterize the type and orientation (positive or negative) of the evaluative stance, as well as its target and possibly its source. Potential applications of these methods include new approaches to the now-traditional tasks of sentiment classification and pinion mining, as well as possibly for adversarial textual analysis and intention detection for intelligence applications.