Effi Levi

Effi Levi, Guy Mor, Tamir Sheafer et al.

Automatic extraction of narrative elements from text, combining narrative theories with computational models, has been receiving increasing attention over the last few years. Previous works have utilized the oral narrative theory by Labov and Waletzky to identify various narrative elements in personal stories texts. Instead, we direct our focus to informational texts, specifically news stories. We introduce NEAT (Narrative Elements AnnoTation) - a novel NLP task for detecting narrative elements in raw text. For this purpose, we designed a new multi-label narrative annotation scheme, better suited for informational text (e.g. news media), by adapting elements from the narrative theory of Labov and Waletzky (Complication and Resolution) and adding a new narrative element of our own (Success). We then used this scheme to annotate a new dataset of 2,209 sentences, compiled from 46 news articles from various category domains. We trained a number of supervised models in several different setups over the annotated dataset to identify the different narrative elements, achieving an average F1 score of up to 0.77. The results demonstrate the holistic nature of our annotation scheme as well as its robustness to domain category.

Gal Ron, Effi Levi, Odelia Oshri et al.

In this work we propose a novel annotation scheme which factors hate speech into five separate discursive categories. To evaluate our scheme, we construct a corpus of over 2.9M Twitter posts containing hateful expressions directed at Jews, and annotate a sample dataset of 1,050 tweets. We present a statistical analysis of the annotated dataset as well as discuss annotation examples, and conclude by discussing promising directions for future work.

Effi Levi, Shaul R. Shenhav

We propose a novel method to conceptually decompose an existing annotation into separate levels, allowing the analysis of inter-annotators disagreement in each level separately. We suggest two distinct strategies in order to actualize this approach: a theoretically-driven one, in which the researcher defines a decomposition based on prior knowledge of the annotation task, and an exploration-based one, in which many possible decompositions are inductively computed and presented to the researcher for interpretation and evaluation. Utilizing a recently constructed dataset for narrative analysis as our use-case, we apply each of the two strategies to demonstrate the potential of our approach in testing hypotheses regarding the sources of annotation disagreements, as well as revealing latent structures and relations within the annotation task. We conclude by suggesting how to extend and generalize our approach, as well as use it for other purposes.

Dror K. Markus, Effi Levi, Tamir Sheafer et al.

Media Storms, dramatic outbursts of attention to a story, are central components of media dynamics and the attention landscape. Despite their significance, there has been little systematic and empirical research on this concept due to issues of measurement and operationalization. We introduce an iterative human-in-the-loop method to identify media storms in a large-scale corpus of news articles. The text is first transformed into signals of dispersion based on several textual characteristics. In each iteration, we apply unsupervised anomaly detection to these signals; each anomaly is then validated by an expert to confirm the presence of a storm, and those results are then used to tune the anomaly detection in the next iteration. We demonstrate the applicability of this method in two scenarios: first, supplementing an initial list of media storms within a specific time frame; and second, detecting media storms in new time periods. We make available a media storm dataset compiled using both scenarios. Both the method and dataset offer the basis for comprehensive empirical research into the concept of media storms, including characterizing them and predicting their outbursts and durations, in mainstream media or social media platforms.

Effi Levi, Gal Ron, Odelia Oshri et al.

We introduce a novel multi-labeled scheme for joint annotation of hate and counter-hate speech in social media conversations, categorizing hate and counter-hate messages into thematic and rhetorical dimensions. The thematic categories outline different discursive aspects of each type of speech, while the rhetorical dimension captures how hate and counter messages are communicated, drawing on Aristotle's Logos, Ethos and Pathos. We annotate a sample of 92 conversations, consisting of 720 tweets, and conduct statistical analyses, incorporating public metrics, to explore patterns of interaction between the thematic and rhetorical dimensions within and between hate and counter-hate speech. Our findings provide insights into the spread of hate messages on social media, the strategies used to counter them, and their potential impact on online behavior.

Guy Mor-Lan, Effi Levi

We explore the relationship between factuality and Natural Language Inference (NLI) by introducing FactRel -- a novel annotation scheme that models \textit{factual} rather than \textit{textual} entailment, and use it to annotate a dataset of naturally occurring sentences from news articles. Our analysis shows that 84\% of factually supporting pairs and 63\% of factually undermining pairs do not amount to NLI entailment or contradiction, respectively, suggesting that factual relationships are more apt for analyzing media discourse. We experiment with models for pairwise classification on the new dataset, and find that in some cases, generating synthetic data with GPT-4 on the basis of the annotated dataset can improve performance. Surprisingly, few-shot learning with GPT-4 yields strong results on par with medium LMs (DeBERTa) trained on the labelled dataset. We hypothesize that these results indicate the fundamental dependence of this task on both world knowledge and advanced reasoning abilities.

Effi Levi, Guy Mor, Shaul Shenhav et al.

This paper addresses the task of automatically detecting narrative structures in raw texts. Previous works have utilized the oral narrative theory by Labov and Waletzky to identify various narrative elements in personal stories texts. Instead, we direct our focus to news articles, motivated by their growing social impact as well as their role in creating and shaping public opinion. We introduce CompRes -- the first dataset for narrative structure in news media. We describe the process in which the dataset was constructed: first, we designed a new narrative annotation scheme, better suited for news media, by adapting elements from the narrative theory of Labov and Waletzky (Complication and Resolution) and adding a new narrative element of our own (Success); then, we used that scheme to annotate a set of 29 English news articles (containing 1,099 sentences) collected from news and partisan websites. We use the annotated dataset to train several supervised models to identify the different narrative elements, achieving an $F_1$ score of up to 0.7. We conclude by suggesting several promising directions for future work.

Effi Levi, Saggy Herman, Ari Rappoport

Clustering a lexicon of words is a well-studied problem in natural language processing (NLP). Word clusters are used to deal with sparse data in statistical language processing, as well as features for solving various NLP tasks (text categorization, question answering, named entity recognition and others). Spectral clustering is a widely used technique in the field of image processing and speech recognition. However, it has scarcely been explored in the context of NLP; specifically, the method used in this (Meila and Shi, 2001) has never been used to cluster a general word lexicon. We apply spectral clustering to a lexicon of words, evaluating the resulting clusters by using them as features for solving two classical NLP tasks: semantic role labeling and dependency parsing. We compare performance with Brown clustering, a widely-used technique for word clustering, as well as with other clustering methods. We show that spectral clusters produce similar results to Brown clusters, and outperform other clustering methods. In addition, we quantify the overlap between spectral and Brown clusters, showing that each model captures some information which is uncaptured by the other.

Gali Noti, Effi Levi, Yoav Kolumbus et al.

A large body of work in behavioral fields attempts to develop models that describe the way people, as opposed to rational agents, make decisions. A recent Choice Prediction Competition (2015) challenged researchers to suggest a model that captures 14 classic choice biases and can predict human decisions under risk and ambiguity. The competition focused on simple decision problems, in which human subjects were asked to repeatedly choose between two gamble options. In this paper we present our approach for predicting human decision behavior: we suggest to use machine learning algorithms with features that are based on well-established behavioral theories. The basic idea is that these psychological features are essential for the representation of the data and are important for the success of the learning process. We implement a vanilla model in which we train SVM models using behavioral features that rely on the psychological properties underlying the competition baseline model. We show that this basic model captures the 14 choice biases and outperforms all the other learning-based models in the competition. The preliminary results suggest that such hybrid models can significantly improve the prediction of human decision making, and are a promising direction for future research.

Effi Levi, Roi Reichart, Ari Rappoport

The run time complexity of state-of-the-art inference algorithms in graph-based dependency parsing is super-linear in the number of input words (n). Recently, pruning algorithms for these models have shown to cut a large portion of the graph edges, with minimal damage to the resulting parse trees. Solving the inference problem in run time complexity determined solely by the number of edges (m) is hence of obvious importance. We propose such an inference algorithm for first-order models, which encodes the problem as a minimum spanning tree (MST) problem in an undirected graph. This allows us to utilize state-of-the-art undirected MST algorithms whose run time is O(m) at expectation and with a very high probability. A directed parse tree is then inferred from the undirected MST and is subsequently improved with respect to the directed parsing model through local greedy updates, both steps running in O(n) time. In experiments with 18 languages, a variant of the first-order MSTParser (McDonald et al., 2005b) that employs our algorithm performs very similarly to the original parser that runs an O(n^2) directed MST inference.