The distribution of consumer sentiment is analyzed, key actors in interaction networks are identified, and the extent to which Twitter-based data can complement the evaluation of fragrance co-branding strategy is explored.
Abstract
The rapid growth of the global fragrance industry has driven brands to adopt co-branding strategies to strengthen brand equity and expand market reach, yet consumer responses to these collaborations in digital spaces remain fragmented and difficult to predict. This study analyzes the distribution of consumer sentiment, identifies key actors in interaction networks, and explores the extent to which Twitter-based data can complement the evaluation of fragrance co-branding strategy. Using an exploratory social media analytics approach grounded in Digital Public Sphere theory and Social Network Theory, this study integrates Social Network Analysis with six computational modules, wordcloud analysis, sentiment analysis, text network analysis, emotion analysis, trend analysis, and zero-shot classification, applied to 300 public tweets collected via the SocialX platform during 1–12 January 2026 using fragrance and brand collaboration keywords. Results show that public discourse was lexically dominated by neutral sentiment (88%), while zero-shot classification of the same corpus yielded a positive-leaning distribution (82.33%); these are interpreted as two distinct constructs, evaluative polarity versus semantic stance, alongside a Sentiment Index of +0.28 and a dominant happy-emotion classification (92%). Network analysis identified a small number of actors occupying central or bridging positions in information dissemination, and trend analysis detected two major activity peaks on January 1–2, 2026, coinciding with the New Year transition. These findings offer theoretical implications for applying Digital Public Sphere and Social Network Theory jointly to fragrance co-branding discourse, and practical implications for brand managers seeking to monitor how collaboration discourse is expressed and circulates online.
Social media is a vital platform for policy communication, yet research rarely integrates content and structural features to evaluate communication effects multidimensionally. This study proposes a convergent framework combining text mining and social network analysis to assess policy communication effects and underlying mechanisms. Using China’s upgraded Mass Entrepreneurship and Innovation policy on Sina Weibo as a case, we analyze communication breadth, depth, audience sentiment, thematic focus, network topology, key nodes, and community characteristics. The results reveal that (1) communication breadth is dominated by official communicators, while audiences drive interactive depth, reflecting a “centralized broadcasting, decentralized engagement” model; (2) influential users express more positive attitudes than ordinary audiences; (3) discussions diversify from core innovation themes to micro-level concerns like regional development and talent policies; (4) the network shows loose global structure but strong local clustering, with bridging nodes posting less polarized, broader content. Theoretically, this study offers behavioral-level observations that align with key corollaries of the Spiral of Silence Theory—the tendency for individuals with deviating views to shift toward lower-visibility participation. These pattern-level findings offer a complementary empirical perspective on opinion expression in digital policy contexts. Practically, the findings offer preliminary insights that may inform adaptive, decentralized strategies for enhancing policy diffusion in similar social media contexts.
This study examined the consumers' decisions on how to purchase eyeshadow products from Twitter/X conversations using Sentiment Analysis and Social Network Analysis (SNA). The research aimed to investigate the sentiment of consumers, interaction, influence of influential people, and communication structures of eyeshadow products in the social media marketing and the social media communication. We employed data collected from Twitter/X through SocialX as a quantitative computational social science approach to the research. The dataset comprised 218 records between January 1, 2026, and April 30, 2026, with eyeshadow, e.g., eye-shadow, eye-shadow review, eye-shadow recommendation, and eye-shadow discussion. We combined sentiment analysis, emotion analysis, text network analysis, trend analysis, and social network analysis to investigate consumers’ interactions and information sharing. We find that Twitter/X discussions regarding eyeshadow products are dominated by suggestions, product reviews, and information sharing. As a result, the sentiment analysis showed that neutral and positive sentiment dominated the discussion and the emotional representation was the most dominant emotion. The Social Network Analysis identified several key actors who are in the network and were involved in connecting discussion clusters and communicating cosmetic information. The findings show that the social media interactions were a major factor in the understanding of consumers’ decision to purchase eyeshadow products. The recommendations, positive perception of the product, and the well-connected digital communication structures of Twitter/X have shown that Twitter/X is a very effective source to exchange product information and to shape cosmetic purchasing in beauty online communities.
Auliya Nur Afifah, Vanessa Gaffar, Asep Miftahuddin· Apollo· 0 citations
The blind box phenomenon has created a complex digital conversation ecosystem on Platform X (formerly Twitter), where collector communities exchange information, unboxing experiences, and social validation. This study maps the digital conversation network structure of blind box collector communities on Platform X and traces product information diffusion patterns within it. Data were collected via the SocialX platform using the keywords “blind box” AND (“collector” OR “collection” OR “unboxing” OR “trading”), yielding 995 tweets from 716 unique accounts (January 15 to June 14, 2026), predominantly in English (77.8%) and Indonesian (11.3%). Five analytical methods were integrated: Social Network Analysis (SNA), Dynamic Network Analysis, Trend Analysis, Sentiment Analysis, and Text Network Analysis. The findings reveal a highly fragmented mention network divided into numerous small isolated clusters with content-resharing accounts (such as @youtube) and niche marketplace accounts (such as @chimpershq) emerging as the two dominant hubs. Dynamic network analysis confirmed that both hubs persisted consistently over time, indicating centralized information diffusion concentrated among a small number of actors. Trend analysis identified 11 conversation spikes concentrated in January to February 2026, followed by a significant decline in March to April, before recovering in June 2026. Sentiment analysis showed that community conversations were dominated by positive sentiment (42.71%), followed by neutral (37.59%) and negative (19.70%). Text network analysis revealed that unboxing, collection, series, and secret were the central concepts organizing community discourse. These findings contribute empirically to understanding how niche collector communities form and disseminate information on social media, while offering practical implications for digital marketing strategies targeting collectible product communities.
N. Herliana, E. Surachman, Asep Miftahuddin· Apollo· 0 citations
In recent years, co-branded marketing has become popular throughout the network, and social media plays a crucial role in it. Based on recent market data and user reviews, the great potential of co-branding and the role of social media in it were studied. Descriptive statistics, structural analysis and text analysis are comprehensively used in this study. The study finds that: the scale of co-branded marketing market has continued to grow at a high speed, and the market value and potential are huge; Among them, social media plays three roles of propagation amplifier, user co-creation platform and emotional connector .Their degree of play determine the success or failure of co-branded marketing; Positive comments from users in social media focused on “creativity” and “collection value”, while negative comments focused on “difficulties in rush buying” and “decline in quality”, which revealed that the core of co-branded marketing's success lies in the deep integration of IP and products, and the construction of emotional resonance. This study provides decision-making reference for the company to do co-branding practice in the era of social media.
The rapid growth of social media has transformed political communication by decentralizing information flows and replacing traditional gatekeeping with algorithm-driven content distribution. This shift has significantly influenced democratic participation, opinion formation, electoral mobilization, polarization, and information integrity. This study examines how political narratives are created and amplified through user-generated content, algorithmic curation, and network dynamics. Using a hybrid methodology—combining content analysis, sentiment modeling, network centrality measures, and engagement metrics—the research proposes computational indicators such as the Narrative Amplification Index (NAI), Sentiment Dominance Ratio (SDR), and Polarization Coefficient (PC) to measure narrative influence. Analysis of social media posts during a major electoral cycle reveals that algorithmic amplification strengthens ideological homogeneity and increases cross-group polarization. Approximately 68% of highly engaged political posts contained emotionally charged framing, highlighting the role of affective language in narrative virality. Coordinated networks also contributed significantly to rapid narrative diffusion. The findings demonstrate that social media platforms actively shape political discourse through engagement-driven algorithms, prioritizing emotionally intense and polarizing content. The study provides computational insights into digital political ecosystems and offers implications for policymakers and platform regulators seeking to balance free expression with information integrity
Thomas Fischer, Anna Schmidt· International Journal of Eme...· 0 citations
Research on social media marketing for luxury brands is crucial, as it enables market expansion into new geographic markets, emphasizes digital platforms, redefines luxury, and shifts the research focus from Western perspectives to others. This study reviews articles published from 2010 to 2024 in Scopus, Web of Science, and EBSCO, applying defined inclusion and exclusion criteria, and analyzes 58 articles (n = 58). The research identifies four main themes: social media marketing drivers, consumer segmentation, content strategy, and influencer marketing. Social media marketing drivers encompass attributes such as entertainment, interactivity, trendiness, customization, and word of mouth, as well as perceptions of luxury brand values, particularly psychological distance. Consumer segmentation focuses on the psychological motivation behind consumer engagement with luxury brands on social media. Content strategy investigates the types of messages (text or visual) and their sources (firm- or user-generated). Influencer marketing examines influencer characteristics grounded in source credibility theory, as well as types such as robot, local, or disability influencers. These themes are explored through Western, Asian, general, and diverse perspectives, with research tailored to each. A proposed holistic conceptual research model is presented, offering insights for future studies informed by prior research on social media marketing for luxury brands.
L. Suprawan, Wanny Oentoro· Contemporary Management Rese...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
