Manipulated news online is a growing problem which necessitates the use of automated systems to curtail its spread. We argue that while misinformation and disinformation detection have been studied, there has been a lack of investment in the important open challenge of detecting harmful agendas in news articles; identifying harmful agendas is critical to flag news campaigns with the greatest potential for real world harm. Moreover, due to real concerns around censorship, harmful agenda detectors must be interpretable to be effective. In this work, we propose this new task and release a dataset, \textsc{NewsAgendas}, of annotated news articles for agenda identification. We show how interpretable systems can be effective on this task and demonstrate that they can perform comparably to black-box models.

Towards Detecting Harmful Agendas in News Articles

A major issue with using deep learning models in sensitive applications is that they provide no explanation for their output. To address this problem, unsupervised selective rationalization produces rationales alongside predictions by chaining two jointly-trained components, a rationale generator and a predictor. Although this architecture guarantees that the prediction relies solely on the rationale, it does not ensure that the rationale contains a plausible explanation for the prediction. We introduce a novel training technique that effectively limits generation of implausible rationales by injecting noise between the generator and the predictor. Furthermore, we propose a new benchmark for evaluating unsupervised selective rationalization models using movie reviews from existing datasets. We achieve sizeable improvements in rationale plausibility and task accuracy over the state-of-the-art across a variety of tasks, including our new benchmark, while maintaining or improving model faithfulness.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/11bd972d-4e65-457d-994e-c765c53b73b8" width="300" height="400"></iframe>

Unsupervised Selective Rationalization with Noise Injection

### [Program](https://wassa-workshop.github.io/2023/schedule/)
Subjectivity and Sentiment Analysis has become a highly developed research area, ranging from binary classification of reviews to the detection of complex emotion structures between entities found in text. This field has expanded both on a practical level, finding numerous successful applications in business, as well as on a theoretical level, allowing researchers to explore more complex research questions related to affective computing. Its continuing importance is also shown by the interest it generates in other disciplines such as Economics, Sociology, Psychology, Marketing, Crisis Management & Digital Humanities.<br>For more details visit our workshop website: https://wassa-workshop.github.io/
#### [Visit GatherTown](https://app.gather.town/app/5OscLswEEuYf2Psb/ACL2023)

W16: The 13th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA)

workshop paper

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
<br>The conference will be held in Toronto, Canada, July 9-14, 2023.<br><br>
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience.<br>
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**
<br><br><br><br>

ACL 2023

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

Poster Session 5

poster

interpretability

noise

news

plausibility

disinformation

rationalization

llms

political biases

unsupervised selective rationalization

selective rationalization

noise injection

agenda detection

prompt brittleness

multimodal interaction; multimodal prediction; sarcasm detection; humor detection

Melanie Subbiah

2

1

SHORT BIO

Presentations

Towards Detecting Harmful Agendas in News Articles

Unsupervised Selective Rationalization with Noise Injection

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES