Valerie L. Shalin

S. M. Seals, Valerie L. Shalin

Psycholinguistic analyses provide a means of evaluating large language model (LLM) output and making systematic comparisons to human-generated text. These methods can be used to characterize the psycholinguistic properties of LLM output and illustrate areas where LLMs fall short in comparison to human-generated text. In this work, we apply psycholinguistic methods to evaluate individual sentences from long-form analogies about biochemical concepts. We compare analogies generated by human subjects enrolled in introductory biochemistry courses to analogies generated by chatGPT. We perform a supervised classification analysis using 78 features extracted from Coh-metrix that analyze text cohesion, language, and readability (Graesser et. al., 2004). Results illustrate high performance for classifying student-generated and chatGPT-generated analogies. To evaluate which features contribute most to model performance, we use a hierarchical clustering approach. Results from this analysis illustrate several linguistic differences between the two sources.

Spencer M. Seals, Valerie L. Shalin

The development of highly fluent large language models (LLMs) has prompted increased interest in assessing their reasoning and problem-solving capabilities. We investigate whether several LLMs can solve a classic type of deductive reasoning problem from the cognitive science literature. The tested LLMs have limited abilities to solve these problems in their conventional form. We performed follow up experiments to investigate if changes to the presentation format and content improve model performance. We do find performance differences between conditions; however, they do not improve overall performance. Moreover, we find that performance interacts with presentation format and content in unexpected ways that differ from human performance. Overall, our results suggest that LLMs have unique reasoning biases that are only partially predicted from human reasoning performance and the human-generated language corpora that informs them.

Thilini Wijesiriwardene, Amit Sheth, Valerie L. Shalin et al.

A hallmark of intelligence is the ability to use a familiar domain to make inferences about a less familiar domain, known as analogical reasoning. In this article, we delve into the performance of Large Language Models (LLMs) in dealing with progressively complex analogies expressed in unstructured text. We discuss analogies at four distinct levels of complexity: lexical analogies, syntactic analogies, semantic analogies, and pragmatic analogies. As the analogies become more complex, they require increasingly extensive, diverse knowledge beyond the textual content, unlikely to be found in the lexical co-occurrence statistics that power LLMs. To address this, we discuss the necessity of employing Neuro-symbolic AI techniques that combine statistical and symbolic AI, informing the representation of unstructured text to highlight and augment relevant content, provide abstraction and guide the mapping process. Our knowledge-informed approach maintains the efficiency of LLMs while preserving the ability to explain analogies for pedagogical applications.

S. M. Seals, Valerie L. Shalin

The summarization of conversation, that is, discourse over discourse, elevates pragmatic considerations as a pervasive limitation of both summarization and other applications of contemporary conversational AI. Building on impressive progress in both semantics and syntax, pragmatics concerns meaning in the practical sense. In this paper, we discuss several challenges in both summarization of conversations and other conversational AI applications, drawing on relevant theoretical work. We illustrate the importance of pragmatics with so-called star sentences, syntactically acceptable propositions that are pragmatically inappropriate in conversation or its summary. Because the baseline for quality of AI is indistinguishability from human behavior, we draw heavily on the psycho-linguistics literature, and label our complaints as "Turing Test Triggers" (TTTs). We discuss implications for the design and evaluation of conversation summarization methods and conversational AI applications like voice assistants and chatbots

S. M. Seals, Valerie L. Shalin

Despite considerable performance improvements, current conversational AI systems often fail to meet user expectations. We discuss several pragmatic limitations of current conversational AI systems. We illustrate pragmatic limitations with examples that are syntactically appropriate, but have clear pragmatic deficiencies. We label our complaints as "Turing Test Triggers" (TTTs) as they indicate where current conversational AI systems fall short compared to human behavior. We develop a taxonomy of pragmatic considerations intended to identify what pragmatic competencies a conversational AI system requires and discuss implications for the design and evaluation of conversational AI systems.

Goonmeet Bajaj, Srinivasan Parthasarathy, Valerie L. Shalin et al.

Grounding is a challenging problem, requiring a formal definition and different levels of abstraction. This article explores grounding from both cognitive science and machine learning perspectives. It identifies the subtleties of grounding, its significance for collaborative agents, and similarities and differences in grounding approaches in both communities. The article examines the potential of neuro-symbolic approaches tailored for grounding tasks, showcasing how they can more comprehensively address grounding. Finally, we discuss areas for further exploration and development in grounding.

Trilok Padhi, Ugur Kursuncu, Yaman Kumar et al.

The digital landscape continually evolves with multimodality, enriching the online experience for users. Creators and marketers aim to weave subtle contextual cues from various modalities into congruent content to engage users with a harmonious message. This interplay of multimodal cues is often a crucial factor in attracting users' attention. However, this richness of multimodality presents a challenge to computational modeling, as the semantic contextual cues spanning across modalities need to be unified to capture the true holistic meaning of the multimodal content. This contextual meaning is critical in attracting user engagement as it conveys the intended message of the brand or the organization. In this work, we incorporate external commonsense knowledge from knowledge graphs to enhance the representation of multimodal data using compact Visual Language Models (VLMs) and predict the success of multi-modal crowdfunding campaigns. Our results show that external knowledge commonsense bridges the semantic gap between text and image modalities, and the enhanced knowledge-infused representations improve the predictive performance of models for campaign success upon the baselines without knowledge. Our findings highlight the significance of contextual congruence in online multimodal content for engaging and successful crowdfunding campaigns.

Swati Padhee, Anurag Illendula, Megan Sadler et al.

Dementia is a group of irreversible, chronic, and progressive neurodegenerative disorders resulting in impaired memory, communication, and thought processes. In recent years, clinical research advances in brain aging have focused on the earliest clinically detectable stage of incipient dementia, commonly known as mild cognitive impairment (MCI). Currently, these disorders are diagnosed using a manual analysis of neuropsychological examinations. We measure the feasibility of using the linguistic characteristics of verbal utterances elicited during neuropsychological exams of elderly subjects to distinguish between elderly control groups, people with MCI, people diagnosed with possible Alzheimer's disease (AD), and probable AD. We investigated the performance of both theory-driven psycholinguistic features and data-driven contextual language embeddings in identifying different clinically diagnosed groups. Our experiments show that a combination of contextual and psycholinguistic features extracted by a Support Vector Machine improved distinguishing the verbal utterances of elderly controls, people with MCI, possible AD, and probable AD. This is the first work to identify four clinical diagnosis groups of dementia in a highly imbalanced dataset. Our work shows that machine learning algorithms built on contextual and psycholinguistic features can learn the linguistic biomarkers from verbal utterances and assist clinical diagnosis of different stages and types of dementia, even with limited data.

Thilini Wijesiriwardene, Hale Inan, Ugur Kursuncu et al.

The convenience of social media has also enabled its misuse, potentially resulting in toxic behavior. Nearly 66% of internet users have observed online harassment, and 41% claim personal experience, with 18% facing severe forms of online harassment. This toxic communication has a significant impact on the well-being of young individuals, affecting mental health and, in some cases, resulting in suicide. These communications exhibit complex linguistic and contextual characteristics, making recognition of such narratives challenging. In this paper, we provide a multimodal dataset of toxic social media interactions between confirmed high school students, called ALONE (AdoLescents ON twittEr), along with descriptive explanation. Each instance of interaction includes tweets, images, emoji and related metadata. Our observations show that individual tweets do not provide sufficient evidence for toxic behavior, and meaningful use of context in interactions can enable highlighting or exonerating tweets with purported toxicity.

Rahul Pandey, Hemant Purohit, Carlos Castillo et al.

High-quality human annotations are necessary for creating effective machine learning-driven stream processing systems. We study hybrid stream processing systems based on a Human-In-The-Loop Machine Learning (HITL-ML) paradigm, in which one or many human annotators and an automatic classifier (trained at least partially by the human annotators) label an incoming stream of instances. This is typical of many near-real-time social media analytics and web applications, including annotating social media posts during emergencies by digital volunteer groups. From a practical perspective, low-quality human annotations result in wrong labels for retraining automated classifiers and indirectly contribute to the creation of inaccurate classifiers. Considering human annotation as a psychological process allows us to address these limitations. We show that human annotation quality is dependent on the ordering of instances shown to annotators and can be improved by local changes in the instance sequence/order provided to the annotators, yielding a more accurate annotation of the stream. We adapt a theoretically-motivated human error framework of mistakes and slips for the human annotation task to study the effect of ordering instances (i.e., an "annotation schedule"). Further, we propose an error-avoidance approach to the active learning paradigm for stream processing applications robust to these likely human errors (in the form of slips) when deciding a human annotation schedule. We support the human error framework using crowdsourcing experiments and evaluate the proposed algorithm against standard baselines for active learning via extensive experimentation on classification tasks of filtering relevant social media posts during natural disasters.

Hussein S. Al-Olimat, Valerie L. Shalin, Krishnaprasad Thirunarayan et al.

Imprecise composite location references formed using ad hoc spatial expressions in English text makes the geocoding task challenging for both inference and evaluation. Typically such spatial expressions fill in unestablished areas with new toponyms for finer spatial referents. For example, the spatial extent of the ad hoc spatial expression "north of" or "50 minutes away from" in relation to the toponym "Dayton, OH" refers to an ambiguous, imprecise area, requiring translation from this qualitative representation to a quantitative one with precise semantics using systems such as WGS84. Here we highlight the challenges of geocoding such referents and propose a formal representation that employs background knowledge, semantic approximations and rules, and fuzzy linguistic variables. We also discuss an appropriate evaluation technique for the task that is based on human contextualized and subjective judgment.

Mohammadreza Rezvan, Saeedeh Shekarpour, Faisal Alshargi et al.

Disclaimer: This paper is concerned with violent online harassment. To describe the subject at an adequate level of realism, examples of our collected tweets involve violent, threatening, vulgar and hateful speech language in the context of racial, sexual, political, appearance and intellectual harassment. The presence of a significant amount of harassment in user-generated content and its negative impact calls for robust automatic detection approaches. This requires that we can identify different forms or types of harassment. Earlier work has classified harassing language in terms of hurtfulness, abusiveness, sentiment, and profanity. However, to identify and understand harassment more accurately, it is essential to determine the context that represents the interrelated conditions in which they occur. In this paper, we introduce the notion of contextual type to harassment involving five categories: (i) sexual, (ii) racial, (iii) appearance-related, (iv) intellectual and (v) political. We utilize an annotated corpus from Twitter distinguishing these types of harassment. To study the context for each type that sheds light on the linguistic meaning, interpretation, and distribution, we conduct two lines of investigation: an extensive linguistic analysis, and a statistical distribution of unigrams. We then build type-ware classifiers to automate the identification of type-specific harassment. Our experiments demonstrate that these classifiers provide competitive accuracy for identifying and analyzing harassment on social media. We present extensive discussion and major observations about the effectiveness of type-aware classifiers using a detailed comparison setup providing insight into the role of type-dependent features.

Saeedeh Shekarpour, Ankita Saxena, Krishnaprasad Thirunarayan et al.

The ever-growing datasets published on Linked Open Data mainly contain encyclopedic information. However, there is a lack of quality structured and semantically annotated datasets extracted from unstructured real-time sources. In this paper, we present principles for developing a knowledge graph of interlinked events using the case study of news headlines published on Twitter which is a real-time and eventful source of fresh information. We represent the essential pipeline containing the required tasks ranging from choosing background data model, event annotation (i.e., event recognition and classification), entity annotation and eventually interlinking events. The state-of-the-art is limited to domain-specific scenarios for recognizing and classifying events, whereas this paper plays the role of a domain-agnostic road-map for developing a knowledge graph of interlinked events.