Learning alignments from legislative discourse

Kauffman, Daniel; Khosmood, Foaad; Kuboi, Toshihiro; Dekhtyar, Alex

doi:10.1145/3209281.3209413

Cited by 7 publications

(8 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use high quality, human-verified transcripts from hearings in the California state legislature as developed by the Digital Democracy project [3] and already used in several other works [4,9,12,14]. The specific training set, engagement and affiliation statistics we use can be found online 1 .…”

Section: Datamentioning

confidence: 99%

Feature Engineering for US State Legislative Hearings: Stance, Affiliation, Engagement and Absentees

Grace¹,

Khosmood²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

In US State government legislatures, most of the activity occurs in committees made up of lawmakers discussing bills. When analyzing, classifying or summarizing these committee proceedings, some important features become broadly interesting. In this paper, we engineer four useful features, two applying to lawmakers (engagement and absence), and two to non-lawmakers (stance and affiliation). We propose a system to automatically track the affiliation of organizations in public comments and whether the organizational representative supports or opposes the bill. The model tracking affiliation achieves an F1 of 0.872 while the support determination has an F1 of 0.979. Additionally, a metric to compute legislator engagement and absenteeism is also proposed and as proof-of-concept, a list of the most and least engaged legislators over one full California legislative session is presented.

show abstract

Section: Datamentioning

confidence: 99%

Feature Engineering for US State Legislative Hearings: Stance, Affiliation, Engagement and Absentees

Grace¹,

Khosmood²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Sentiment polarity analysis is often used as part of an NLP pipeline as a subtask of a different opinion mining task, such as agreement detection (Salah et al, 2013a). Similarly, Kauffman et al (2018) use sentiment analysis as a sub-task and the output scores as features for allignment detection, while Duthie & Budzynska (2018) do similar for ethos detection, and Budhwar et al (2018) aim to predict vote outcome using the results of sentiment polarity analysis as features for the task. Conversely, Burfoot (2008) applies the results of classification by party affiliation to predict speaker sentiment.…”

Section: Tasksmentioning

confidence: 99%

“…For others (n = 24), analysis is conducted at the utterance or "speech segment" level (that is, an unbroken passage of speech by the same speaker), although Akhmedovaet et al (2018) refer to these as "interventions", and Bansal et al A further eight papers report analysis at the speaker level. That is, they consider a document to be the concatenation of all speeches given by the same representative (Bonica, 2016;Diermeier et al, 2012;Kauffman et al, 2018;Kim et al, 2018;Owen, 2017;Schwarz et al, 2017;Taddy, 2013).…”

Section: Granularitymentioning

confidence: 99%

“…Dzieciątko (2018) classifies speakers as expressing happiness, anger, sadness, fear, or disgust, while Rheault (2016) attempts to identify the level of anxiety exhibited by speakers, and Honkela et al (2014) analyse a corpus of congressional speeches under the PERMA (Positive emotion, Engagement, Relationships, Meaning, and Achievement) model. 2 Agreement detection, an end in itself for Ahmadalinezhad & Makrehchi(2018)andKauffman et al (2018), is used by andBurfood et al (2015) to predict speaker sentiment, while Salah et al(2013a) use agreement information to construct debate graphs. Finally, automatically compare speeches with another type of labelled text (statements from online debates) to identify positive and negative framing of arguments.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Sentiment and position-taking analysis of parliamentary debates: a systematic literature review

Abercrombie

Batista-Navarro

2020

J Comput Soc Sc

View full text Add to dashboard Cite

Parliamentary and legislative debate transcripts provide access to information concerning the opinions, positions and policy preferences of elected politicians. They attract attention from researchers from a wide variety of backgrounds, from political and social sciences to computer science. As a result, the problem of automatic sentiment and position-taking analysis has been tackled from different perspectives, using varying approaches and methods, and with relatively little collaboration or cross-pollination of ideas. The existing research is scattered across publications from various fields and venues. In this article we present the results of a systematic literature review of 61 studies, all of which address the automatic analysis of the sentiment and opinions expressed and positions taken by speakers in parliamentary (and other legislative) debates. In this review, we discuss the available research with regard to the aims and objectives of the researchers who work on these problems, the automatic analysis tasks they undertake, and the approaches and methods they use.We conclude by summarizing their findings, discussing the challenges of applying computational analysis to parliamentary debates, and suggesting possible avenues for further research.

show abstract

“…We found that Vader was able to sufficiently analyze our legislator utterances. In September of 2017, Daniel Kauffman built a system that used a legislator's utterance to determine their alignment toward a known entity [24]. This allowed users to predict a legislator's alignment with specific organizations with know views.…”

Section: Vader Sentimentmentioning

confidence: 99%

DiSH: Democracy in State Houses

Russo

View full text Add to dashboard Cite

In our current political climate, state level legislators have become increasingly important. Due to cuts in funding and growing focus at the national level, public oversight for these legislators has drastically decreased. This makes it difficult for citizens and activists to understand the relationships and commonalities between legislators. This thesis provides three contributions to address this issue. First, we created a data set containing over 1200 features focused on a legislator's activity on bills. Second, we created embeddings that represented a legislator's level of activity and engagement for a given bill using a custom model called Democracy2Vec. Third, we provided a case study focused on the 2015-2016 California State Legislator and had our results verified by a political expert. Our results show that our embeddings can explain relationships between legislator and how they will likely act during the legislative process. iv ACKNOWLEDGMENTS Thanks to:• My family, for their unwavering love and support throughout this process.• Bailey Blair, for constantly supporting me and pushing me to be my best.• My advisor, Alex Dekhtyar, for shaping my career through his indispensable advice and guidance.• My committee members, Foaad Khosmood and Franz Kurfess, for their feedback and assistance throughout this unusual process.• Daniel Kauffman, for letting me use his bill topic modeling system.

show abstract

Learning alignments from legislative discourse

Cited by 7 publications

References 1 publication

Feature Engineering for US State Legislative Hearings: Stance, Affiliation, Engagement and Absentees

Feature Engineering for US State Legislative Hearings: Stance, Affiliation, Engagement and Absentees

Sentiment and position-taking analysis of parliamentary debates: a systematic literature review

DiSH: Democracy in State Houses

Contact Info

Product

Resources

About