CS 6322: Affect Processing from Social Media - IT Assignment Help

Assignment Task:

Task:

1. The Problem (2 points): Describe briefly how you generate an affect processing system operating on Twitter postings. The main affect that is processed is the stance for misinformation targets related to COVID-19 vaccines. In addition, affect is processed though:

o sentiment recognition, which is compared with and integrated in the stance detection system;
o emotion detection, which is analyzed and integrated in the stance detection system;
o topic detection, which is compared against the targets of misinformation and integrated in the stance detection system;
o affect connotation frames, resulting from the analysis of the integration of semantic role labeling and named entity recognition and their integration and in the stance detection system;

The entire team describes what you learned, what was you experience, what were the difficulties you faced and how you resolved them.

Phase A of the project (20 points – based on quality of annotations).

The team is provided with a dataset of tweets, and a set of misinformation targets. The team annotates the stance of each misinformation expressed in each tweet with:
(a) The tweet AGREES with the misinformation target
(b) The tweet DISAGREES with the misinformation target
(c) The tweet has NO STANCE towards the misinformation target
(d) The tweet is NOT_RELEVANT for the misinformation target

Phase B : The team uses for training ONLY the whole set of annotated tweets produced by all the members of the team during Phase A combined with a new annotated dataset provided to the team on April 18 as the training set and from it sets a Development set for Phase B of the project, when each student develops its own neural architecture and trains it and prepares it for demonstration.

2. Stance Detection (40 points): written by the student that was responsible for this task – A Figure of the neural architecture (10 points) is provided as well as the equations, input/output explanation. How the architecture was trained and what results it obtained on the development set (10 points). A Baseline architecture using BERT shall be also trained and presents– detailing what results this baseline architecture obtained on the Development set (10 points). How the stance detection was made available for the other affect processing tasks developed by other members of the team (10 points). Make sure that the name of the student appears prominently, along with the student netID on every page of the description of the stance detection (5 points will be deducted if name/netID are missing). Additional 35 points will be obtained if during the Demo of the system, in front of the entire class, the system is able to detect the stance on several new tweets.

3. Sentiment Recognition for Affect Processing (40 points): written by the student that fine-tuned a neural sentiment detection system on the training data produced by the team on Phase A of the project. A Figure of the neural architecture for sentiment recognition (5 points) and a Figure for its incorporation in the stance detection system (10 points) is provided as well as the equations, input/output explanation. How sentiment recognition was tuned on the training set (10 points) and how the stance detection using sentiment recognition was trained and what results it obtained on the development set (10 points). Elaborate on how you have collaborated with the student responsible for the stance detection for incorporating sentiment detection (5 points). Make sure that the name of the student appears prominently, along with the student netID on every page of the description of the sentiment recognition and its incorporation into stance detection (5 points will be deducted if name/netID are missing). Additional 35 points will be obtained if during the Demo of the system, in front of the entire class, the system is able to detect the sentiment and the stance on several new tweets.

4. Emotion Detection for Affect Processing (40 points): written by the student that fine-tuned a neural emotion recognition system on the training data produced by the team on Phase A of the project. A Figure of the neural architecture for emotion recognition (5 points) and a Figure for its incorporation in the stance detection system (10 points) is provided as well as the equations, input/output explanation. How emotion recognition was tuned on the training set (10 points) and how the stance detection using emotion recognition was trained and what results it obtained on the development set (10 points).

This  CS 6322: IT Assignment has been solved by our IT experts at My Uni Paper. Our Assignment Writing Experts are efficient to provide a fresh solution to this question. We are serving more than 10000+ Students in Australia, UK & US by helping them to score HD in their academics. Our Experts are well trained to follow all marking rubrics & referencing style.

Be it a used or new solution, the quality of the work submitted by our assignment experts remains unhampered. You may continue to expect the same or even better quality with the used and new assignment solution files respectively. There’s one thing to be noticed that you could choose one between the two and acquire an HD either way. You could choose a new assignment solution file to get yourself an exclusive, plagiarism (with free Turnitin file), expert quality assignment or order an old solution file that was considered worthy of the highest distinction.