Indiana University-Purdue University Indianapolis (IUPUI) / Since the use of social media has evolved, the ability of its users to bully others has increased. One of the prevalent forms of bullying is Cyberbullying, which occurs on the social media sites such as Facebook©, WhatsApp©, and Twitter©. The past decade has witnessed a growth in cyberbullying – is a form of bullying that occurs virtually by the use of electronic devices, such as messaging, e-mail, online gaming, social media, or through images or mails sent to a mobile. This bullying is not only limited to English language and occurs in other languages. Hence, it is of the utmost importance to detect cyberbullying in multiple languages. Since current approaches to identify cyberbullying are mostly focused on English language texts, this thesis proposes a new approach (called Multilingual Cyberbullying Detection System) for the detection of cyberbullying in multiple languages (English, Hindi, and Marathi). It uses two techniques, namely, Machine Learning-based and Lexicon-based, to classify the input data as bullying or non-bullying. The aim of this research is to not only detect cyberbullying but also provide a distributed infrastructure to detect bullying. We have developed multiple prototypes (standalone, collaborative, and cloud-based) and carried out experiments with them to detect cyberbullying on different datasets from multiple languages. The outcomes of our experiments show that the machine-learning model outperforms the lexicon-based model in all the languages. In addition, the results of our experiments show that collaboration techniques can help to improve the accuracy of a poor-performing node in the system. Finally, we show that the cloud-based configurations performed better than the local configurations.

京都大学 / 0048 / 新制・課程博士 / 博士(工学) / 甲第19694号 / 工博第4149号 / 新制||工||1640(附属図書館) / 32730 / 京都大学大学院工学研究科都市社会工学専攻 / (主査)教授 小林 潔司, 教授 藤井 聡, 准教授 松島 格也 / 学位規則第4条第1項該当 / Doctor of Philosophy (Engineering) / Kyoto University / DFAM

No description available.

[Context and motivation]: Incompleteness in natural-language requirements is a challenging problem. [Question/Problem]: A common technique for detecting incompleteness in requirements is checking the requirements against external sources. With the emergence of language models such as BERT, an interesting question is whether language models are useful external sources for finding potential incompleteness in requirements. [Principal ideas/results]: We mask words in requirements and have BERT's masked language model (MLM) generate contextualized predictions for filling the masked slots. We simulate incompleteness by withholding content from requirements and measure BERT's ability to predict terminology that is present in the withheld content but absent in the content disclosed to BERT. [Contributions]: BERT can be configured to generate multiple predictions per mask. Our first contribution is to determine how many predictions per mask is an optimal trade-off between effectively discovering omissions in requirements and the level of noise in the predictions. Our second contribution is devising a machine learning-based filter that post-processes predictions made by BERT to further reduce noise. We empirically evaluate our solution over 40 requirements specifications drawn from the PURE dataset [30]. Our results indicate that: (1) predictions made by BERT are highly effective at pinpointing terminology that is missing from requirements, and (2) our filter can substantially reduce noise from the predictions, thus making BERT a more compelling aid for improving completeness in requirements.

No description available.

A lot of interaction between humans take place on social media. Groups and communities are sometimes formed both with and without intention. These interactions generate a large quantity of text data. This project aims to detect dissimilarity in discourse between communities on social media using a distributed approach. A data set of tweets was used to test and evaluate the method. Tweets produced from two communities were extracted from the data set. Two Natural Language Processing techniques were used to vectorise the tweets for each community. Namely LIWC, dictionary based on knowledge acquired from professionals in linguistics and psychology, and BERT, an embedding model which uses machine learning to present words and sentences as a vector of decimal numbers. These vectors were then used as representations of the text to measure the similarity of discourse between the communities. Both distance and similarity were measured. It was concluded that none of the combinations of measure or vectorisation method that was tried could detect a dissimilarity in discourse on social media for the sample data set.

Sentiment transfer involves changing the sentiment of a sentence, such as from a positive to negative sentiment, whilst maintaining the informational content. Whilst this challenge in the NLP research domain can be constructed as a translation problem, traditional sequence-to-sequence translation methods are inadequate due to the dearth of parallel corpora for sentiment transfer. Thus, sentiment transfer can be posed as an unsupervised learning problem where a model must learn to transfer from one sentiment to another in the absence of parallel sentences. Given that the sentiment of a sentence is often defined by a limited number of sentiment-specific words within the sentence, this problem can also be posed as a problem of identifying and altering sentiment-specific words as a means of transferring from one sentiment to another. In this dissertation we use a novel method of sentiment word identification from the interpretability literature called the method of rationales. This method identifies the words or phrases in a sentence that explain the ‘rationale' for a classifier's class prediction, in this case the sentiment of a sentence. This method is then compared against a baseline heuristic sentiment word identification method. We also experiment with a pretrained encoder-decoder Transformer model, known as BART, as a method for improving upon previous sentiment transfer results. This pretrained model is fine-tuned first in an unsupervised manner as a denoising autoencoder to reconstruct sentences where sentiment words have been masked out. This fine-tuned model then generates a parallel corpus which is used to further fine-tune the final stage of the model in a self-supervised manner. Results were compared against a baseline using automatic evaluations of accuracy and BLEU score as well as human evaluations of content preservation, sentiment accuracy and sentence fluency. The results of this dissertation show that both neural network and heuristic-based methods of sentiment word identification achieve similar results across models for similar levels of sentiment word removal for the Yelp dataset. However, the heuristic approach leads to improved results with the pretrained model on the Amazon dataset. We also find that using the pretrained Transformers model improves upon the results of using the baseline LSTM trained from scratch for the Yelp dataset for all automatic metrics. The pretrained BART model scores higher across all human-evaluated outputs for both datasets, which is likely due to its larger size and pretraining corpus. These results also show a similar trade-off between content preservation and sentiment transfer accuracy as in previous research, with more favourable results on the Yelp dataset relative to the baseline.

No description available.

No description available.

The California state legislature introduces approximately 5,000 new bills each legislative session. While the legislative hearings are recorded on video, the recordings are not easily accessible to the public. The lack of official transcripts or summaries also increases the effort required to gain meaningful insight from those recordings. Therefore, the news media and the general population are largely oblivious to what transpires during legislative sessions. Digital Democracy, a project started by the Cal Poly Institute for Advanced Technology and Public Policy, is an online platform created to bring transparency to the California legislature. It features a searchable database of state legislative committee hearings, with each hearing accompanied by a transcript that was generated by an internal transcription tool. This thesis presents SKEWER, a pipeline for building a spoken-word knowledge graph from those transcripts. SKEWER utilizes a number of natural language processing tools to extract named entities, phrases, and sentiments from the transcript texts and aggregates the results of those tools into a graph database. The resulting graph can be queried to discover knowledge regarding the positions of legislators, lobbyists, and the general public towards specific bills or topics, and how those positions are expressed in committee hearings. Several case studies are presented to illustrate the new knowledge that can be acquired from the knowledge graph.