No description available.

Machine Learning is improving at being able to analyze data and find patterns in it, but does machine learning have the capabilities to predict something subjective like a movie’s rating using exclusively objective data such as actors, directors, genres, and their runtime? Previous research has shown the profit and performance of actors on certain genres are somewhat predictable. Other studies have had reasonable results using subjective data such as how many likes the actors and directors have on Facebook or what people say about the movie on Twitter and YouTube. This study presents several machine learning algorithms using data provided by IMDb in order to predict the ratings also provided by IMDb and which features of a movie have the biggest impact on its performance. This study found that almost all conducted algorithms are on average 0.7 stars away from the real rating which might seem quite accurate, but at the same time, 85% of movies have ratings between 5 and 8, which means the importance of the data used seems less relevant.

This thesis aims to understand the emotions expressed by adults watching animated films with death topics through sentiment analysis. The research is a quantitative sentiment analysis from the perspective of distant reading. The previous studies on death scenes in animated films have only focused on child audiences. However, the age group of the audience of animated films is extensive; thus, it is necessary to analyse the sentiments of adult audiences. This thesis attempts to collect two movies produced by Pixar studio: Coco (2017) and Soul (2020), as well as their audience reviews on IMDb, a total of 600, for cross-comparison. Additionally, it analyses the content containing death in the reviews to understand better adult audiences’ emotional expressions on the subject of death. The analysing results show that the positive sentiment scores of the comments containing death are slightly lower than the scores of all the reviews, and the scores of the negative sentiments do not differ much. However, positive emotions still dominate these comments that contain death. The emotional performance between the script and the reviews is roughly similar. Still, the emotional intensity of the comments is higher than that of the script, indicating that the audience is willing to show their emotions on the public online film platform. Future research is recommended to conduct analysis together with other NLP analysis methods or close reading to explore more details of the content.

In today’s modern digital world more and more emails and messengers must be sent, processed and handled. The categorizing and classification of these text pieces can take an incredibly long time and will cost the company a lot of time and money. If the classification could be done automatically by a computer dependent on the content of the text/message it would result in a major yield for the Easit AB and its customers. In order to facilitate the task of text-classification Easit needs a solution that is made out of one language model and one classifier model. The language model will convert raw text to a vector that is representative of the text and the classifier will construe what predefined labels fit for the vector. The end goal is not to create the best solution. It is simply to create a general understanding about different language and classifier models and how to build a system that will be both fast and accurate. BERT were the primary language model during evaluation but doc2Vec and One-Hot encoding was also tested. The classifier consisted out of boundary condition models or dense neural networks that were all trained without knowledge about what language model that the text vectors came from. The validation accuracy which was presented for the IMDB-comment dataset with BERT resulted between 75% to 94%, mostly dependent on the language model and not on the classifier. The knowledge from the work resulted in a recommendation to Easit for an alternativebased system solution. / I dagens moderna digitala värld är det allt mer majl-ärenden och meddelanden som ska skickas och processeras. Kategorisering och klassificering av dessa kan ta otroligt lång tid och kostar företag tid samt pengar. Om klassifieringen kunde ske automatiskt beroende på text-innehållet skulle det innebära en stor vinst för Easit AB och deras kunder.  För att underlätta arbetet med text-klassifiering behöver Easit en tvådelad lösning som består utav en språkmodell och en klassifierare. Språkmodellen som omvandlar text till en vektor som representerar texten och klassifieraren tolkar vilka fördefinerade ettiketter/märken som passar för vektorn. Målet är inte att skapa den bästa lösningen utan det är att skapa en generell kunskap för hur man kan utforma ett system som kan klassifiera texten på ett träffsäkert och effektivt sätt. Vid utvärdering av olika språkmodeller användes framförallt BERT-modeller men även doc2Vec och One-Hot testas också. Klassifieraren bestod utav gränsvillkors-modeller eller dense neurala nätverk som tränades helt utan vetskap om vilken språkmodell som skickat text-vektorerna. Träffsäkerheten som uppvisades vid validering för IMDB-kommentars datasetet med BERT blev mellan 75% till 94%, primärt beroende på språkmodellen. De neuralt nätverk passar bäst som klassifierare mest på grund av deras skalbarhet med flera ettiketter. Kunskapen från arbetet resulterade i en rekommendation till Easit om en alternativbaserad systemlösning.

The thesis examines how users of the Internet Movie Database (IMDb) negotiate feminism in their reviews of four superheroine films – Wonder Woman, Captain Marvel, Birds of Prey: The Fantabulous Emancipation of One Harley Quinn, and Wonder Woman 1984. By combining critical discourse analysis with methods of corpus linguists, this corpus-based study of over 18,000 reviews analyses the frequency of the topic of feminism in the reviews, words and topics associated with it and the way the reviewers reflect broader mediated discourse over the four films, and the role of IMDb as a space for these reviews. The findings show that feminism is still understood as an anti-male movement where female-led films are shielded from criticism by the mainstream media by the virtue of the lead’s gender, the superheroines are criticised for being overpowered particularly where they have no equal male supporting character and that perceived feminist messaging is usually written off as a forced political agenda or as an insincere cash grab made by corporates which effectively use feminism for promotion. It also reveals IMDb as a highly polarised platform where the users leaving 1- and 10-star reviews are generalized as representatives of different sides of the political spectrum (antifeminist vs feminist, conservative vs liberal) regardless of the actual content of the review.

No description available.

Background: Movies have become an important marketing and advertising tool that can influence consumer behaviour and trends. Reading film reviews is an im- important part of watching a movie, as it can help viewers gain a general under- standing of the film. And also, provide filmmakers with feedback on how their work is being received. Sentiment analysis is a method of determining whether a review has positive or negative sentiment, and this study investigates a machine learning method for classifying sentiment from film reviews. Objectives: This thesis aims to perform comparative sentiment analysis on textual IMDb movie reviews using lexicon-based and BERT neural network models. Later different performance evaluation metrics are used to identify the most effective learning model. Methods: This thesis employs a quantitative research technique, with data analysed using traditional machine learning. The labelled data set comes from an online website called Kaggle (https://www.kaggle.com/datasets), which contains movie review information. Algorithms like the lexicon-based approach and the BERT neural networks are trained using the chosen IMDb movie reviews data set. To discover which model performs the best at predicting the sentiment analysis, the constructed models will be assessed on the test set using evaluation metrics such as accuracy, precision, recall and F1 score. Results: From the conducted experimentation the BERT neural network model is the most efficient algorithm in classifying the IMDb movie reviews into positive and negative sentiments. This model achieved the highest accuracy score of 90.67% over the trained data set, followed by the BoW model with an accuracy of 79.15%, whereas the TF-IDF model has 78.98% accuracy. BERT model has the better precision and recall with 0.88 and 0.92 respectively, followed by both BoW and TF-IDF models. The BoW model has a precision and recall of 0.79 and the TF-IDF has a precision of 0.79 and a recall of 0.78. And also the BERT model has the highest F1 score of 0.88, followed by the BoW model having a F1 score of 0.79 whereas, TF-IDF has 0.78. Conclusions: Among the two models evaluated, the lexicon-based approach and the BERT transformer neural network, the BERT neural network is the most efficient, having a good performance score based on the measured performance criteria.

Backdoor (Trojan) attacks are a major threat to the security of deep neural network (DNN) models. They are created by an attacker who adds a certain pattern to a portion of given training dataset, causing the DNN model to misclassify any inputs that contain the pattern. These infected classifiers are called Trojan models and the added pattern is referred to as the trigger. In image domain, a trigger can be a patch of pixel values added to the images and in text domain, it can be a set of words. In this thesis, we propose Trojan-Miner (T-Miner), a defense scheme against such backdoor attacks on text classification deep learning models. The goal of T-Miner is to detect whether a given classifier is a Trojan model or not. To create T-Miner , our approach is based on a sequence-to-sequence text generation model. T-Miner uses feedback from the suspicious (test) classifier to perturb input sentences such that their resulting class label is changed. These perturbations can be different for each of the inputs. T-Miner thus extracts the perturbations to determine whether they include any backdoor trigger and correspondingly flag the suspicious classifier as a Trojan model. We evaluate T-Miner on three text classification datasets: Yelp Restaurant Reviews, Twitter Hate Speech, and Rotten Tomatoes Movie Reviews. To illustrate the effectiveness of T-Miner, we evaluate it on attack models over text classifiers. Hence, we build a set of clean classifiers with no trigger in their training datasets and also using several trigger phrases, we create a set of Trojan models. Then, we compute how many of these models are correctly marked by T-Miner. We show that our system is able to detect trojan and clean models with 97% overall accuracy over 400 classifiers. Finally, we discuss the robustness of T-Miner in the case that the attacker knows T-Miner framework and wants to use this knowledge to weaken T-Miner performance. To this end, we propose four different scenarios for the attacker and report the performance of T-Miner under these new attack methods. / M.S. / Backdoor (Trojan) attacks are a major threat to the security of predictive models that make use of deep neural networks. The idea behind these attacks is as follows: an attacker adds a certain pattern to a portion of given training dataset and in the next step, trains a predictive model over this dataset. As a result, the predictive model misclassifies any inputs that contain the pattern. In image domain this pattern that is called trigger, can be a patch of pixel values added to the images and in text domain, it can be a set of words. In this thesis, we propose Trojan-Miner (T-Miner), a defense scheme against such backdoor attacks on text classification deep learning models. The goal of T-Miner is to detect whether a given classifier is a Trojan model or not. T-Miner is based on a sequence-to-sequence text generation model that is connected to the given predictive model and determine if the predictive model is being backdoor attacked. When T-Miner is connected to the predictive model, it generates a set of words, called perturbations, and analyses these perturbations to determine whether they include any backdoor trigger. Hence if any part of the trigger is present in the perturbations, the predictive model is flagged as a Trojan model. We evaluate T-Miner on three text classification datasets: Yelp Restaurant Reviews, Twitter Hate Speech, and Rotten Tomatoes Movie Reviews. To illustrate the effectiveness of T-Miner, we evaluate it on attack models over text classifiers. Hence, we build a set of clean classifiers with no trigger in their training datasets and also using several trigger phrases, we create a set of Trojan models. Then, we compute how many of these models are correctly marked by T-Miner. We show that our system is able to detect Trojan models with 97% overall accuracy over 400 predictive models.