Online hatred has become an increasingly pervasive issue, affecting individuals and communities across various digital platforms. To combat hate speech in such platforms, counter narratives (CNs) are regarded as an effective method. In recent years, there has been growing interest in using generative AI tools to construct CNs. However, most of the generative models produce generic responses to hate speech and can hallucinate, reducing their effectiveness. To address the above limitations, we propose a counter narrative generation method that enhances CNs by providing non-aggressive, fact-based narratives with relevant background knowledge from two distinct sources, including a web search module. Furthermore, we conduct a comprehensive evaluation using multiple metrics, including LLM-based measures for persuasion, factuality, and informativeness, along with human and traditional NLP evaluations. Our method significantly outperforms baselines, achieving an average factuality score of 0.915, compared to 0.741, 0.701, and 0.69 for competitive baselines, and performs well in human evaluations.

The patent citation count is a good indicator of patent quality.This often generates monetary value for the inventors and organizations.However, the factors that influence a patent receiving high citations over the year are still not well understood.With the patents over the past two decades, we study the problem of patent citation prediction and formulate this as a binary classification problem.We create a semantic graph of patents based on their semantic similarities, enabling the use of Graph Neural Network (GNN)-based approaches for predicting citations.Our experimental results demonstrate the effectiveness of our GNN-based methods when applied to the semantic graph, showing that they can accurately predict patent citations using only patent text.More specifically, these methods produce up to 94% recall for patents with high citations and outperform existing baselines.Furthermore, we leverage this constructed graph to gain insights and explanations for the predictions made by the GNNs.

Having more followers has become a norm in recent social media and micro-blogging communities. This battle has been taking shape from the early days of Twitter. Despite this strong competition for followers, many Twitter users are continuously losing their followers. This work addresses the problem of identifying the reasons behind the drop of followers of users in Twitter. As a first step, we extract various features by analyzing the content of the posts made by the Twitter users who lose followers consistently. We then leverage these features to early detect follower loss. We propose various models and yield an overall accuracy of 73% with high precision and recall. Our model outperforms baseline model by 19.67% (w.r.t accuracy), 33.8% (w.r.t precision) and 14.3% (w.r.t recall).

Goodreads has launched the Readers Choice Awards since 2009 where users are able to nominate/vote books of their choice, released in the given year. In this work, we question if the number of votes that a book would receive (aka the popularity of the book) can be predicted based on the characteristics of various entities on Goodreads. We are successful in predicting the popularity of the books with high prediction accuracy (correlation coefficient ~0.61) and low RMSE (~1.25). User engagement and author's prestige are found to be crucial factors for book popularity.

In this paper, we investigate the problem of building automatic classifiers to categorize opinions and facts into appropriate subcategories. While working on two English News article datasets and two social media datasets (Twitter hashtag idioms and Youtube comments), we achieve consistent performance with accuracies in the range of 70-85% for opinion and fact sub-categorization. The proposed classifiers can be instrumental in understanding argumentative relations as well as in developing fact-checking systems. It can also be used to detect anomalous behavior such as predominant drunkers or other psychological changes.

In the last decade, social media has evolved as one of the leading platform to create, share, or exchange information; it is commonly used as a way for individuals to maintain social connections. In this online digital world, people use to post texts or pictures to express their views socially and create user-user engagement through discussions and conversations. Thus, social media has established itself to bear signals relating to human behavior. One can easily design user characteristic network by scraping through someone’s social media profiles. In this paper, we investigate the potential of social media in characterizing and understanding predominant drunk texters from the perspective of their social, psychological and linguistic behavior as evident from the content generated by them. Our research aims to analyze the behavior of drunk texters on social media and to contrast this with non-drunk texters. We use Twitter social media to obtain the set of drunk texters and non-drunk texters and show that we can classify users into these two respective sets using various psycholinguistic features with an overall average accuracy of 96.78% with very high precision and recall. Note that such an automatic classification can have far-reaching impact – (i) on health research related to addiction prevention and control, and (ii) in eliminating abusive and vulgar contents from Twitter, borne by the tweets of drunk texters.

In Twitter, there is a rising trend in abusive behavior which often leads to incivility. This trend is affecting users mentally and as a result they tend to leave Twitter and other such social networking sites thus depleting the active user base. In this paper, we study factors associated with incivility. We observe that the act of incivility is highly correlated with the opinion differences between the account holder (i.e., the user writing the incivil tweet) and the target (i.e., the user for whom the incivil tweet is meant for or targeted), toward a named entity. We introduce a character level CNN model and incorporate the entity-specific sentiment information for efficient incivility detection which significantly outperforms multiple baseline methods achieving an impressive accuracy of 93.3% (4.9% improvement over the best baseline). In a post-hoc analysis, we also study the behavioral aspects of the targets and account holders and try to understand the reasons behind the incivility incidents. Interestingly, we observe that there are strong signals of repetitions in incivil behavior. In particular, we find that there are a significant fraction of account holders who act as repeat offenders - attacking the targets even more than 10 times. Similarly, there are also targets who get targeted multiple times. In general, the targets are found to have higher reputation scores than the account holders.

Quora is one of the most popular community question & answer (Q&A) sites of recent times. However, with increasing question posts over time and the posts covering a wide range of topics (unlike focused Q&A sites like Stack Overflow), not all of them are getting answered. Measuringanswerability(i.e., whether a question shall get answered or not) involves collecting expensive human judgment data that can differentiate the characteristics of an answered question from an unanswered (akaopen) one. Factors to judge if a question would remain open include its subjectivity, openendedness, vagueness, ambiguity, and so on. It is difficult to collect such judgments for thousands of questions, requiring automatic framework to deal the issue of answerability of questions. In this paper, we quantify: 1)user-leveland 2)question-level linguistic activities—that cannicely correspond to many of the judgment factors noted earlier, can beeasily measured for each question postand thatappropriately discriminates an answered question from an unanswered one. Our central finding is thatthe way users use language while writing the question text can be a very effective means to characterize answerability.This characterization further helps us to predict early if a question remaining unanswered for a specific time period$t$will eventually be answered or not and achieve an accuracy of 76.26% ($t=1$month) and 68.33% ($t=3$months). Notably, features representing thelanguage use patternsof the users are most discriminative and alone account for an accuracy of 74.18%. We also compare our method with some of the similar works[1],[2]achieving a maximum improvement of ~39% in terms of accuracy.

Success of a book depends on various intrinsic and extrinsic parameters. We perform a cross-platform study of book reading behavior on Goodreads and attempt to establish the connection between the Goodreads entities and the Amazon best sellers. We analyze the collective reading behavior on Goodreads platform and quantify various characteristic features of the Goodreads entities to identify differences between the Amazon best sellers (ABS) and the other non-best selling books. Using these features we devise a model to predict if a book shall become a best seller after one month (15 days) since its publication. On a balanced set, we are able to achieve a very high avg. accuracy of 88.72% (85.66%) for the prediction where the other competitive class contains books which are randomly selected from the Goodreads dataset. Our method primarily based on features derived from user posts and genre related characteristic properties achieves an improvement of 16.4% over the traditional popularity factors (ratings, reviews) based baseline methods.

Compounding of natural language units is a very common phenomena. In this paper, we show, for the first time, that Twitter hashtags which, could be considered as correlates of such linguistic units, undergo compounding. We identify reasons for this compounding and propose a prediction model that can identify with 77.07% accuracy if a pair of hashtags compounding in the near future (i.e., 2 months after compounding) shall become popular. At longer times T = 6, 10 months the accuracies are 77.52% and 79.13% respectively. This technique has strong implications to trending hashtag recommendation since newly formed hashtag compounds can be recommended early, even before the compounding has taken place. Further, humans can predict compounds with an overall accuracy of only 48.7% (treated as baseline). Notably, while humans can discriminate the relatively easier cases, the automatic framework is successful in classifying the relatively harder cases.

Abstract In this paper, we propose an unsupervised and automated method to identify noun sense changes based on rigorous analysis of time-varying text data available in the form of millions of digitized books and millions of tweets posted per day. We construct distributional-thesauri-based networks from data at different time points and cluster each of them separately to obtain word-centric sense clusters corresponding to the different time points. Subsequently, we propose a split/join based approach to compare the sense clusters at two different time points to find if there is ‘birth’ of a new sense. The approach also helps us to find if an older sense was ‘split’ into more than one sense or a newer sense has been formed from the ‘join’ of older senses or a particular sense has undergone ‘death’. We use this completely unsupervised approach (a) within the Google books data to identify word sense differences within a media, and (b) across Google books and Twitter data to identify differences in word sense distribution across different media. We conduct a thorough evaluation of the proposed methodology both manually as well as through comparison with WordNet.