Complex and Ambiguous

Cha, Yoonjeong; Kim, Jong-Won; Park, Sangkeun; Yi, Mun Yong; Lee, Uichin

doi:10.1145/3274299

Cited by 16 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, we plan to investigate feature selection methods [99,100] that could potentially reduce the complexity and increase the performance of the classifiers. To improve accuracy we also plan to extend our analysis by considering emoji and emoticon symbols, which are pervasive in SM content, as studied in [101,102]. Finally, we plan to design conversation agents capable of participating in some discussions [103] during online conversations, based on the learned conversational patterns, to implement nudging and hinting strategies towards the users.…”

Section: Discussionmentioning

confidence: 99%

Graph-Based Conversation Analysis in Social Media

Brambilla

Sabet

Kharmale

et al. 2022

BDCC

View full text Add to dashboard Cite

Social media platforms offer their audience the possibility to reply to posts through comments and reactions. This allows social media users to express their ideas and opinions on shared content, thus opening virtual discussions. Most studies on social networks have focused only on user relationships or on the shared content, while ignoring the valuable information hidden in the digital conversations, in terms of structure of the discussion and relation between contents, which is essential for understanding online communication behavior. This work proposes a graph-based framework to assess the shape and structure of online conversations. The analysis was composed of two main stages: intent analysis and network generation. Users’ intention was detected using keyword-based classification, followed by the implementation of machine learning-based classification algorithms for uncategorized comments. Afterwards, human-in-the-loop was involved in improving the keyword-based classification. To extract essential information on social media communication patterns among the users, we built conversation graphs using a directed multigraph network and we show our model at work in two real-life experiments. The first experiment used data from a real social media challenge and it was able to categorize 90% of comments with 98% accuracy. The second experiment focused on COVID vaccine-related discussions in online forums and investigated the stance and sentiment to understand how the comments are affected by their parent discussion. Finally, the most popular online discussion patterns were mined and interpreted. We see that the dynamics obtained from conversation graphs are similar to traditional communication activities.

show abstract

Section: Discussionmentioning

confidence: 99%

Graph-Based Conversation Analysis in Social Media

Brambilla

Sabet

Kharmale

et al. 2022

BDCC

View full text Add to dashboard Cite

show abstract

“…This is especially true for comments that may be complex and ambiguous (e.g. Cha et al ., 2018). The authors are also unable to determine the motivation associated with each comment.…”

Section: Implications and Limitationsmentioning

confidence: 99%

Social media fashion influencer eWOM communications: understanding the trajectory of sustainable fashion conversations on YouTube fashion haul videos

Haines

Fares

Mohan

et al. 2023

JFMM

View full text Add to dashboard Cite

PurposeThis study aims to examine YouTube comments relevant to sustainable fashion posted on fashion haul videos over the past decade (2011–2021). It is guided by two research questions: (1) How have sustainable fashion-related comments posted on YouTube fashion haul videos changed over time? and (2) What themes are relevant to sustainable fashion in the comments posted on fashion haul videos?Design/methodology/approachA data set of comments from 110 fashion haul videos posted on YouTube was refined to only include comments with keywords related to sustainable fashion. Leximancer, a machine learning technique, was employed to identify concepts within the data and co-occurrences between concepts. Linguistic Inquiry and Word Count software was employed to assess the prevalence of concepts and identify sentiment over time.FindingsOver the decade, the authors identified increased comments and conversations relevant to sustainable fashion. For instance, conversations surrounding sustainable fashion were linked to “waste” and “addicted” between 2011 and 2013, which evolved to include “environment” and “clothes” between 2014 and 2016, to “buy” and “workers” between 2017 and 2019 and “sustainable” between 2020 and 2021, demonstrating the changes in conversation topics over time.Practical implicationsWith increasing engagement from YouTube viewers on sustainable fashion, retail-affiliated content that promotes sustainable fashion is proposed as one approach to engage viewers and promote sustainable practices in the fashion industry, whereby content creators can partner with retailers to feature products and educate viewers on the benefits of sustainable fashion.Originality/valueThe findings suggest that consumers are becoming more aware of and responsive to sustainable fashion. The originality of this research stems from identifying the source of this interest.

show abstract

“…While they found a gender effect in the understanding of the message, Rodrigues et al (2018) did not find a gender effect in their findings. Cha et al (2018) examined stickers which are images or animation objects. Although they could convey richer meaning than emoji, the findings showed us that they may be misinterpreted, too.…”

Section: Related Workmentioning

confidence: 99%

Interpretation of Emoji-Only Messages by Message Producers and Receivers

Akadal

Söyük²

2022

International Journal of Technology and Human Interaction

View full text Add to dashboard Cite

Emoji play a significant role in mutual communication. It was seen that emoji might carry different meanings depending on groups or cultures, although they are considered as a language valid for everyone. This study investigated how individuals responded to the questions directed to them using emoji, how they described the basic emotions, and what the individuals who read these messages understood. The study consisted of two stages. At the first stage, the participants were asked to respond to 10 questions, for which answers with concrete and abstract contents were sought, by using first emoji-only and then only text. Moreover, they were requested to express the eight basic emotions they were shown only with emoji. The participants also determined a satisfaction level for the emoji responses. At the second stage, a different group of participants scored the satisfaction levels by displaying the question. It was found out that a message consisting of emoji might be evaluated by the receiver in a different way, even if it has been created with a high satisfaction level.

show abstract

Complex and Ambiguous

Cited by 16 publications

References 26 publications

Graph-Based Conversation Analysis in Social Media

Graph-Based Conversation Analysis in Social Media

Social media fashion influencer eWOM communications: understanding the trajectory of sustainable fashion conversations on YouTube fashion haul videos

Interpretation of Emoji-Only Messages by Message Producers and Receivers

Contact Info

Product

Resources

About