Urban legends are a genre of modern folklore, consisting of stories about rare and exceptional events, just plausible enough to be believed, which tend to propagate inexorably across communities. In our view, while urban legends represent a form of "sticky" deceptive text, they are marked by a tension between the credible and incredible. They should be credible like a news article and incredible like a fairy tale to go viral. In particular we will focus on the idea that urban legends should mimic the details of news (who, where, when) to be credible, while they should be emotional and readable like a fairy tale to be catchy and memorable. Using NLP tools we will provide a quantitative analysis of these prototypical characteristics. We also lay out some machine learning experiments showing that it is possible to recognize an urban legend using just these simple features.
Deriving prior polarity lexica for sentiment analysis - where positive or negative scores are associated with words out of context - is a challenging task. Usually, a trade-off between precision and coverage is hard to find, and it depends on the methodology used to build the lexicon. Manually annotated lexica provide a high precision but lack in coverage, whereas automatic derivation from pre-existing knowledge guarantees high coverage at the cost of a lower precision. Since the automatic derivation of prior polarities is less time consuming than manual annotation, there has been a great bloom of these approaches, in particular based on the SentiWordNet resource. In this paper, we compare the most frequently used techniques based on SentiWordNet with newer ones and blend them in a learning framework (a so called 'ensemble method'). By taking advantage of manually built prior polarity lexica, our ensemble method is better able to predict the prior value of unseen words and to outperform all the other SentiWordNet approaches. Using this technique we have built SentiWords, a prior polarity lexicon of approximately 155,000 words, that has both a high precision and a high coverage. We finally show that in sentiment analysis tasks, using our lexicon allows us to outperform both the single metrics derived from SentiWordNet and popular manually annotated sentiment lexica.
While the effect of various lexical, syntactic, semantic and stylistic features have been addressed in persuasive language from a computational point of view, the persuasive effect of phonetics has received little attention. By modeling a notion of euphony and analyzing four datasets comprising persuasive and non-persuasive sentences in different domains (political speeches, movie quotes, slogans and tweets), we explore the impact of sounds on different forms of persuasiveness. We conduct a series of analyses and prediction experiments within and across datasets. Our results highlight the positive role of phonetic devices on persuasion.
This article provides a comprehensive investigation on the relations between virality of news articles and the emotions they are found to evoke. Virality, in our view, is a phenomenon with many facets, i.e. under this generic term several different effects of persuasive communication are comprised. By exploiting a high-coverage and bilingual corpus of documents containing metrics of their spread on social networks as well as a massive affective annotation provided by readers, we present a thorough analysis of the interplay between evoked emotions and viral facets. We highlight and discuss our findings in light of a cross-lingual approach: while we discover differences in evoked emotions and corresponding viral effects, we provide preliminary evidence of a generalized explanatory model rooted in the deep structure of emotions: the Valence-Arousal-Dominance (VAD) circumplex. We find that viral facets appear to be consistently affected by particular VAD configurations, and these configurations indicate a clear connection with distinct phenomena underlying persuasive communication.
While many lexica annotated with words polarity are available for sentiment analysis, very few tackle the harder task of emotion analysis and are usually quite limited in coverage. In this paper, we present a novel approach for extracting - in a totally automated way - a high-coverage and high-precision lexicon of roughly 37 thousand terms annotated with emotion scores, called DepecheMood. Our approach exploits in an original way 'crowd-sourced' affective annotation implicitly provided by readers of news articles from rappler.com. By providing new state-of-the-art performances in unsupervised settings for regression and classification tasks, even using a na\"{\i}ve approach, our experiments show the beneficial impact of harvesting social media data for affective lexicon building.
Given the fast rise of increasingly autonomous artificial agents and robots, a key acceptability criterion will be the possible moral implications of their actions. In particular, intelligent persuasive systems (systems designed to influence humans via communication) constitute a highly sensitive topic because of their intrinsically social nature. Still, ethical studies in this area are rare and tend to focus on the output of the required action. Instead, this work focuses on the persuasive acts themselves (e.g. "is it morally acceptable that a machine lies or appeals to the emotions of a person to persuade her, even if for a good end?"). Exploiting a behavioral approach, based on human assessment of moral dilemmas -- i.e. without any prior assumption of underlying ethical theories -- this paper reports on a set of experiments. These experiments address the type of persuader (human or machine), the strategies adopted (purely argumentative, appeal to positive emotions, appeal to negative emotions, lie) and the circumstances. Findings display no differences due to the agent, mild acceptability for persuasion and reveal that truth-conditional reasoning (i.e. argument validity) is a significant dimension affecting subjects' judgment. Some implications for the design of intelligent persuasive systems are discussed.
Assigning a positive or negative score to a word out of context (i.e. a word's prior polarity) is a challenging task for sentiment analysis. In the literature, various approaches based on SentiWordNet have been proposed. In this paper, we compare the most often used techniques together with newly proposed ones and incorporate all of them in a learning framework to see whether blending them can further improve the estimation of prior polarity scores. Using two different versions of SentiWordNet and testing regression and classification models across tasks and datasets, our learning approach consistently outperforms the single metrics, providing a new state-of-the-art approach in computing words' prior polarity for sentiment analysis. We conclude our investigation showing interesting biases in calculated prior polarity scores when word Part of Speech and annotator gender are considered.
Many approaches to sentiment analysis rely on lexica where words are tagged with their prior polarity - i.e. if a word out of context evokes something positive or something negative. In particular, broad-coverage resources like SentiWordNet provide polarities for (almost) every word. Since words can have multiple senses, we address the problem of how to compute the prior polarity of a word starting from the polarity of each sense and returning its polarity strength as an index between -1 and 1. We compare 14 such formulae that appear in the literature, and assess which one best approximates the human judgement of prior polarities, with both regression and classification models.
In recent years there has been a growing interest in crowdsourcing methodologies to be used in experimental research for NLP tasks. In particular, evaluation of systems and theories about persuasion is difficult to accommodate within existing frameworks. In this paper we present a new cheap and fast methodology that allows fast experiment building and evaluation with fully-automated analysis at a low cost. The central idea is exploiting existing commercial tools for advertising on the web, such as Google AdWords, to measure message impact in an ecological setting. The paper includes a description of the approach, tips for how to use AdWords for scientific research, and results of pilot experiments on the impact of affective text variations which confirm the effectiveness of the approach.
This paper aims to shed some light on the concept of virality - especially in social networks - and to provide new insights on its structure. We argue that: (a) virality is a phenomenon strictly connected to the nature of the content being spread, rather than to the influencers who spread it, (b) virality is a phenomenon with many facets, i.e. under this generic term several different effects of persuasive communication are comprised and they only partially overlap. To give ground to our claims, we provide initial experiments in a machine learning framework to show how various aspects of virality can be independently predicted according to content features.