共查询到20条相似文献，搜索用时 17 毫秒
1.
《Information processing & management》2020,57(3):102087
With the rapid development in mobile computing and Web technologies, online hate speech has been increasingly spread in social network platforms since it's easy to post any opinions. Previous studies confirm that exposure to online hate speech has serious offline consequences to historically deprived communities. Thus, research on automated hate speech detection has attracted much attention. However, the role of social networks in identifying hate-related vulnerable community is not well investigated. Hate speech can affect all population groups, but some are more vulnerable to its impact than others. For example, for ethnic groups whose languages have few computational resources, it is a challenge to automatically collect and process online texts, not to mention automatic hate speech detection on social media. In this paper, we propose a hate speech detection approach to identify hatred against vulnerable minority groups on social media. Firstly, in Spark distributed processing framework, posts are automatically collected and pre-processed, and features are extracted using word n-grams and word embedding techniques such as Word2Vec. Secondly, deep learning algorithms for classification such as Gated Recurrent Unit (GRU), a variety of Recurrent Neural Networks (RNNs), are used for hate speech detection. Finally, hate words are clustered with methods such as Word2Vec to predict the potential target ethnic group for hatred. In our experiments, we use Amharic language in Ethiopia as an example. Since there was no publicly available dataset for Amharic texts, we crawled Facebook pages to prepare the corpus. Since data annotation could be biased by culture, we recruit annotators from different cultural backgrounds and achieved better inter-annotator agreement. In our experimental results, feature extraction using word embedding techniques such as Word2Vec performs better in both classical and deep learning-based classification algorithms for hate speech detection, among which GRU achieves the best result. Our proposed approach can successfully identify the Tigre ethnic group as the highly vulnerable community in terms of hatred compared with Amhara and Oromo. As a result, hatred vulnerable group identification is vital to protect them by applying automatic hate speech detection model to remove contents that aggravate psychological harm and physical conflicts. This can also encourage the way towards the development of policies, strategies, and tools to empower and protect vulnerable communities. 相似文献
2.
Shiwei Zhang Xiuzhen Zhang Jeffrey Chan Paolo Rosso 《Information processing & management》2019,56(5):1633-1644
Irony as a literary technique is widely used in online texts such as Twitter posts. Accurate irony detection is crucial for tasks such as effective sentiment analysis. A text’s ironic intent is defined by its context incongruity. For example in the phrase “I love being ignored”, the irony is defined by the incongruity between the positive word “love” and the negative context of “being ignored”. Existing studies mostly formulate irony detection as a standard supervised learning text categorization task, relying on explicit expressions for detecting context incongruity. In this paper we formulate irony detection instead as a transfer learning task where supervised learning on irony labeled text is enriched with knowledge transferred from external sentiment analysis resources. Importantly, we focus on identifying the hidden, implicit incongruity without relying on explicit incongruity expressions, as in “I like to think of myself as a broken down Justin Bieber – my philosophy professor.” We propose three transfer learning-based approaches to using sentiment knowledge to improve the attention mechanism of recurrent neural models for capturing hidden patterns for incongruity. Our main findings are: (1) Using sentiment knowledge from external resources is a very effective approach to improving irony detection; (2) For detecting implicit incongruity, transferring deep sentiment features seems to be the most effective way. Experiments show that our proposed models outperform state-of-the-art neural models for irony detection. 相似文献
3.
A joint learning approach with knowledge injection for zero-shot cross-lingual hate speech detection
Endang Wahyu Pamungkas Valerio Basile Viviana Patti 《Information processing & management》2021,58(4):102544
Hate speech is an increasingly important societal issue in the era of digital communication. Hateful expressions often make use of figurative language and, although they represent, in some sense, the dark side of language, they are also often prime examples of creative use of language. While hate speech is a global phenomenon, current studies on automatic hate speech detection are typically framed in a monolingual setting. In this work, we explore hate speech detection in low-resource languages by transferring knowledge from a resource-rich language, English, in a zero-shot learning fashion. We experiment with traditional and recent neural architectures, and propose two joint-learning models, using different multilingual language representations to transfer knowledge between pairs of languages. We also evaluate the impact of additional knowledge in our experiment, by incorporating information from a multilingual lexicon of abusive words. The results show that our joint-learning models achieve the best performance on most languages. However, a simple approach that uses machine translation and a pre-trained English language model achieves a robust performance. In contrast, Multilingual BERT fails to obtain a good performance in cross-lingual hate speech detection. We also experimentally found that the external knowledge from a multilingual abusive lexicon is able to improve the models’ performance, specifically in detecting the positive class. The results of our experimental evaluation highlight a number of challenges and issues in this particular task. One of the main challenges is related to the issue of current benchmarks for hate speech detection, in particular how bias related to the topical focus in the datasets influences the classification performance. The insufficient ability of current multilingual language models to transfer knowledge between languages in the specific hate speech detection task also remain an open problem. However, our experimental evaluation and our qualitative analysis show how the explicit integration of linguistic knowledge from a structured abusive language lexicon helps to alleviate this issue. 相似文献
4.
5.
《Information processing & management》2023,60(5):103433
Hate speech detection refers broadly to the automatic identification of language that may be considered discriminatory against certain groups of people. The goal is to help online platforms to identify and remove harmful content. Humans are usually capable of detecting hatred in critical cases, such as when the hatred is non-explicit, but how do computer models address this situation? In this work, we aim to contribute to the understanding of ethical issues related to hate speech by analysing two transformer-based models trained to detect hate speech. Our study focuses on analysing the relationship between these models and a set of hateful keywords extracted from the three well-known datasets. For the extraction of the keywords, we propose a metric that takes into account the division among classes to favour the most common words in hateful contexts. In our experiments, we first compared the overlap between the extracted keywords with the words to which the models pay the most attention in decision-making. On the other hand, we investigate the bias of the models towards the extracted keywords. For the bias analysis, we characterize and use two metrics and evaluate two strategies to try to mitigate the bias. Surprisingly, we show that over 50% of the salient words of the models are not hateful and that there is a higher number of hateful words among the extracted keywords. However, we show that the models appear to be biased towards the extracted keywords. Experimental results suggest that fitting models with hateful texts that do not contain any of the keywords can reduce bias and improve the performance of the models. 相似文献
6.
《Information processing & management》2022,59(5):103009
The rapid development of online social media makes Abusive Language Detection (ALD) a hot topic in the field of affective computing. However, most methods for ALD in social networks do not take into account the interactive relationships among user posts, which simply regard ALD as a task of text context representation learning. To solve this problem, we propose a pipeline approach that considers both the context of a post and the characteristics of interaction network in which it is posted. Specifically, our method is divided into pre-training and downstream tasks. First, to capture fine contextual features of the posts, we use Bidirectional Encoder Representation from Transformers (BERT) as Encoder to generate sentence representations. Later, we build a Relation-Special Network according to the semantic similarity between posts as well as the interaction network structural information. On this basis, we design a Relation-Special Graph Neural Network (RSGNN) to spread effective information in the interaction network and learn the classification of texts. The experiment proves that our method can effectively improve the detection effect of abusive posts over three public datasets. The results demonstrate that injecting interaction network structure into the abusive language detection task can significantly improve the detection results. 相似文献
7.
《Information processing & management》2022,59(1):102737
Substantial real cases can be formed in current online medical platforms, constituting potentially rich commercial medical value. In order to obtain the value, it is necessary to mine the preference for user perceived cancer risk in online medical platforms. However, user preference in the platforms varies with medical inquiry text environments, and a user's disease-specific online medical inquiry text environment would also affect his/her behavioral decisions in real time. In this sense, considering the inner relations between different contexts and user preferences under different diseases-specific inquiry text environments and integrating early cancer texts will facilitate the exploration on the law of preference for user perceived cancer risk. Therefore, in this paper, the matrix decomposition and Labeled-LDA models are expanded to propose a context-based method to access the preference for user perceived cancer risk. Firstly, modeling on the relationship between user preferences and information in multi-dimensional context is carried out, and the universal method of integrating multi-dimensional contextual information with user preferences is analyzed. Moreover, more accurate user references were obtained under the multi-dimensional text space and multi-dimensional disease space. Secondly, the similarity relationships between all disease-specific online medical inquiries and early cancer texts are used to obtain user perceived cancer risk, thus knowing the online medical inquiry texts of user cognized diseases and perceiving the cancer risk. Lastly, by accessing the user preferences under different disease topics and user perceived cancer risk in multi-dimensional contexts, the preference for user perceived cancer risk is obtained in a more accurate way. Based on the large-volume real-world dataset, the relationship between each context and user preferences is assessed, and it is concluded that the method proposed in this paper is superior to MF-LDA method in obtaining the preference for user perceived cancer risk. This indicates that the proposed method not only expresses user perceived risk, but also clearly expresses the characteristics of user's preference. Furthermore, it is verified that the integration of context with early cancer text and the establishment of user preference model are feasible and effective. 相似文献
8.
《Information processing & management》2023,60(3):103270
Social media has become the most popular platform for free speech. This freedom of speech has given opportunities to the oppressed to raise their voice against injustices, but on the other hand, this has led to a disturbing trend of spreading hateful content of various kinds. Pakistan has been dealing with the issue of sectarian and ethnic violence for the last three decades and now due to freedom of speech, there is a growing trend of disturbing content about religion, sect, and ethnicity on social media. This necessitates the need for an automated system for the detection of controversial content on social media in Urdu which is the national language of Pakistan. The biggest hurdle that has thwarted the Urdu language processing is the scarcity of language resources, annotated datasets, and pretrained language models. In this study, we have addressed the problem of detecting Interfaith, Sectarian, and Ethnic hatred on social media in Urdu language using machine learning and deep learning techniques. In particular, we have: (1) developed and presented guidelines for annotating Urdu text with appropriate labels for two levels of classification, (2) developed a large dataset of 21,759 tweets using the developed guidelines and made it publicly available, and (3) conducted experiments to compare the performance of eight supervised machine learning and deep learning techniques, for the automated identification of hateful content. In the first step, experiments are performed for the hateful content detection as a binary classification task, and in the second step, the classification of Interfaith, Sectarian and Ethnic hatred detection is performed as a multiclass classification task. Overall, Bidirectional Encoder Representation from Transformers (BERT) proved to be the most effective technique for hateful content identification in Urdu tweets. 相似文献
9.
Basant Agarwal Heri Ramampiaro Helge Langseth Massimiliano Ruocco 《Information processing & management》2018,54(6):922-937
This paper is concerned with paraphrase detection, i.e., identifying sentences that are semantically identical. The ability to detect similar sentences written in natural language is crucial for several applications, such as text mining, text summarization, plagiarism detection, authorship authentication and question answering. Recognizing this importance, we study in particular how to address the challenges with detecting paraphrases in user generated short texts, such as Twitter, which often contain language irregularity and noise, and do not necessarily contain as much semantic information as longer clean texts. We propose a novel deep neural network-based approach that relies on coarse-grained sentence modelling using a convolutional neural network (CNN) and a recurrent neural network (RNN) model, combined with a specific fine-grained word-level similarity matching model. More specifically, we develop a new architecture, called DeepParaphrase, which enables to create an informative semantic representation of each sentence by (1) using CNN to extract the local region information in form of important n-grams from the sentence, and (2) applying RNN to capture the long-term dependency information. In addition, we perform a comparative study on state-of-the-art approaches within paraphrase detection. An important insight from this study is that existing paraphrase approaches perform well when applied on clean texts, but they do not necessarily deliver good performance against noisy texts, and vice versa. In contrast, our evaluation has shown that the proposed DeepParaphrase-based approach achieves good results in both types of texts, thus making it more robust and generic than the existing approaches. 相似文献
10.
On the web, a huge variety of text collections contain knowledge in different expertise domains, such as technology or medicine. The texts are written for different uses and thus for people having different levels of expertise on the domain. Texts intended for professionals may not be understandable at all by a lay person, and texts for lay people may not contain all the detailed information needed by a professional. Many information retrieval applications, such as search engines, would offer better user experience if they were able to select the text sources that best fit the expertise level of the user. In this article, we propose a novel approach for assessing the difficulty level of a document: our method assesses difficulty for each user separately. The method enables, for instance, offering information in a personalised manner based on the user’s knowledge of different domains. The method is based on the comparison of terms appearing in a document and terms known by the user. We present two ways to collect information about the terminology the user knows: by directly asking the users the difficulty of terms or, as a novel automatic approach, indirectly by analysing texts written by the users. We examine the applicability of the methodology with text documents in the medical domain. The results show that the method is able to distinguish between documents written for lay people and documents written for experts. 相似文献
11.
作为一种修辞手法,"反讽"已越来越多地应用于文学作品和人们的日常谈话中。本文作者试图在语言哲学的视角下,以质量准则、礼貌性和真诚性为基本参数,对日常言语行为中的"反讽"话语加以分析,以期读者能够更好地理解"反讽"话语中的哲学含义。 相似文献
12.
《Information processing & management》2020,57(3):102204
Paraphrase detection is an important task in text analytics with numerous applications such as plagiarism detection, duplicate question identification, and enhanced customer support helpdesks. Deep models have been proposed for representing and classifying paraphrases. These models, however, require large quantities of human-labeled data, which is expensive to obtain. In this work, we present a data augmentation strategy and a multi-cascaded model for improved paraphrase detection in short texts. Our data augmentation strategy considers the notions of paraphrases and non-paraphrases as binary relations over the set of texts. Subsequently, it uses graph theoretic concepts to efficiently generate additional paraphrase and non-paraphrase pairs in a sound manner. Our multi-cascaded model employs three supervised feature learners (cascades) based on CNN and LSTM networks with and without soft-attention. The learned features, together with hand-crafted linguistic features, are then forwarded to a discriminator network for final classification. Our model is both wide and deep and provides greater robustness across clean and noisy short texts. We evaluate our approach on three benchmark datasets and show that it produces a comparable or state-of-the-art performance on all three. 相似文献
13.
Racism on the Web: Its rhetoric and marketing 总被引：2，自引：0，他引：2
Lynn Thiesmeyer 《Ethics and Information Technology》1999,1(2):117-125
Poster (1989) and Schiller (1996) point out that electronic communications have the power to change social and political relationships. The ‘new’ discourse of the Internet has political uses in spreading neo-Nazi ideology and action. I look at two kinds of online neo-Nazi discourse: hate speech itself, including text, music, online radio broadcasts, and images that exhort users to act against target groups; and persuasive rhetoric that does not directly enunciate but ultimately promotes or justifies violence. The online location of these discourses poses urgent questions. Does information technology make the re-emergence of prejudicial messages and attitudes swifter and more likely? Does the Internet's wide range of distribution make for more followers and finally more persuasion? 相似文献
14.
《Information processing & management》2022,59(6):103065
Named entity recognition aims to detect pre-determined entity types in unstructured text. There is a limited number of studies on this task for low-resource languages such as Turkish. We provide a comprehensive study for Turkish named entity recognition by comparing the performances of existing state-of-the-art models on the datasets with varying domains to understand their generalization capability and further analyze why such models fail or succeed in this task. Our experimental results, supported by statistical tests, show that the highest weighted F1 scores are obtained by Transformer-based language models, varying from 80.8% in tweets to 96.1% in news articles. We find that Transformer-based language models are more robust to entity types with a small sample size and longer named entities compared to traditional models, yet all models have poor performance for longer named entities in social media. Moreover, when we shuffle 80% of words in a sentence to imitate flexible word order in Turkish, we observe more performance deterioration, 12% in well-written texts, compared to 7% in noisy text. 相似文献
15.
《Information processing & management》2022,59(4):102998
COVID-19 crisis has been accompanied by copious hate speeches widespread on social media. It reinforces the fragmentation of the world, resulting in more significant racial discrimination and distrust between people, leading to crimes, and injuring individuals spiritually or physically. Hate speech is hard to crack for a global recovery in the post-epidemic era. Conducting with Twitter datasets, this paper aims to find the key indicators that influence the trend of hate speech, then builds a Gaussian Spatio-Temporal Mixture (GSTM) model for trends prediction based on the pre-analysis. Findings show that in the early period, the participation of influential users is closely related to the emergence of sentiment peaks, and the interval time is around one week. After hate speech waves up, the indicator of total exposure becomes more critical, suggesting that grass-root release influences at this stage. Compared with three classical time-series predicting models, the GSTM model shows better peak prediction ability and lower residual mean. This work enriches the approaches of predicting unknown but foreseeable hate speeches accompanied by future pandemics. 相似文献
16.
Authorship analysis of electronic texts assists digital forensics and anti-terror investigation. Author identification can be seen as a single-label multi-class text categorization problem. Very often, there are extremely few training texts at least for some of the candidate authors or there is a significant variation in the text-length among the available training texts of the candidate authors. Moreover, in this task usually there is no similarity between the distribution of training and test texts over the classes, that is, a basic assumption of inductive learning does not apply. In this paper, we present methods to handle imbalanced multi-class textual datasets. The main idea is to segment the training texts into text samples according to the size of the class, thus producing a fairer classification model. Hence, minority classes can be segmented into many short samples and majority classes into less and longer samples. We explore text sampling methods in order to construct a training set according to a desirable distribution over the classes. Essentially, by text sampling we provide new synthetic data that artificially increase the training size of a class. Based on two text corpora of two languages, namely, newswire stories in English and newspaper reportage in Arabic, we present a series of authorship identification experiments on various multi-class imbalanced cases that reveal the properties of the presented methods. 相似文献
17.
《Information processing & management》2016,52(6):1004-1017
The rapid growth of documents in different languages, the increased accessibility of electronic documents, and the availability of translation tools have caused cross-lingual plagiarism detection research area to receive increasing attention in recent years. The task of cross-language plagiarism detection entails two main steps: candidate retrieval and assessing pairwise document similarity. In this paper we examine candidate retrieval, where the goal is to find potential source documents of a suspicious text. Our proposed method for cross-language plagiarism detection is a keyword-focused approach. Since plagiarism usually happens in parts of the text, there is a requirement to segment the texts into fragments to detect local similarity. Therefore we propose a topic-based segmentation algorithm to convert the suspicious document to a set of related passages. After that, we use a proximity-based model to retrieve documents with the best matching passages. Experiments show promising results for this important phase of cross-language plagiarism detection. 相似文献
18.
近年尽管针对中文本文分类的研究成果不少，但基于深度学习对中文政策等长文本进行自动分类的研究还不多见。为此，借鉴和拓展传统的数据增强方法，提出集成新时代人民日报分词语料库（NEPD）、简单数据增强（EDA）算法、word2vec和文本卷积神经网络（TextCNN）的NEWT新型计算框架；实证部分，基于中国地方政府发布的科技政策文本进行算法校验。实验结果显示，在取词长度分别为500、750和1 000词的情况下，应用NEWT算法对中文科技政策文本进行分类的效果优于RCNN、Bi-LSTM和CapsNet等传统深度学习模型，F1值的平均提升比例超过13%；同时，NEWT在较短取词长度下能够实现全文输入的近似效果，可以部分改善传统深度学习模型在中文长文本自动分类任务中的计算效率。 相似文献
19.
20.
This paper critically reviews the different types of abstractions and implementations in the hypertext area and proposes that three types of hypertext exist, namely, small-, medium- and large-volume hypertext. For a single person dealing with a single text the prominent issue is the model of the text that the user browses; this is small-volume hypertext. When a few people are involved in creating a few texts, records are maintained as to who created what and when; this is medium-volume hypertext. In large-volume hypertext the document collection is massive and special institutions are responsible for filtering and indexing material against which arbitrarily many other people issue searches. All these aspects of hypertext have in common an abstraction of text as a graph rather than a line and an ultimate goal of facilitating communication among people. 相似文献