DPDian Purworini

Dian Purworini

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Dian Purworini has a total of 57 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Peran Akomodasi Komunikasi dalam Strategi Branding Desa Wisata: Studi Kualitatif Deskriptif di Desa Wisata Jangglengan

    by Naufal Ahnaf Rizal Hartono, Dian Purworini

    Komunikasi menjadi persoalan penting dalam branding desa wisata karena pengelola harus menyampaikan identitas lokal kepada audiens yang berbeda secara budaya, geografis, dan generasional. Penelitian ini bertujuan menganalisis peran akomodasi komunikasi dalam strategi branding Desa Wisata Jangglengan. Penelitian menggunakan pendekatan kualitatif deskriptif dengan pengumpulan data melalui wawancara terhadap tujuh informan dan observasi selama periode Juni–Agustus 2025. Data dianalisis melalui reduksi, penyajian, dan penarikan kesimpulan. Hasil penelitian menunjukkan bahwa pengelola menerapkan strategi convergence, divergence, dan maintenance secara berlapis. Bahasa Indonesia digunakan untuk menjamin keterpahaman audiens lintas daerah, sedangkan bahasa Jawa dan bahasa kekinian mempertahankan identitas lokal sekaligus membangun kedekatan dengan generasi muda. Bahasa Inggris digunakan untuk memfasilitasi komunikasi dengan wisatawan internasional. Branding juga disesuaikan dengan karakter platform: Instagram menonjolkan estetika dan konsistensi identitas visual, sementara TikTok menghadirkan konten yang lebih spontan, aktual, dan relevan bagi pengguna muda. Kolaborasi dengan influencer pariwisata, media nasional, komunitas, dan desa wisata lain memperluas jangkauan sekaligus memperkuat kredibilitas destinasi. Penelitian ini menunjukkan bahwa akomodasi komunikasi dalam branding desa wisata tidak hanya berlangsung melalui penyesuaian bahasa, tetapi juga melalui adaptasi platform dan pemilihan mitra komunikasi yang sesuai dengan identitas destinasi.

  • Open Access

    Connecting the dots: pathways to fostering communicative processes of resilience in village tourism organizations as a response to the pandemic crisis

    by Dian Purworini, Laili Etika Rahmawati, Rini Darmastuti, Sidiq Setyawan, Agus Triyono

    This study examines the communication process in building resilience in rural tourism by comparing two tourism villages in Sukoharjo Regency, Central Java Province, Indonesia. A qualitative approach was employed, with data collected through two focus group discussions, observations, and documentation involving 19 informants from the two tourism villages. The data were analysed inductively using thematic analysis supported by NVivo 15 software. The findings identify six components of the communicative processes of resilience: the attitudes and commitment of tourism village activists, the role and support of the village government, community participation, communication among tourism village actors, adaptive responses, and economic innovation. Although both villages share similar components, the pathways through which the communicative processes of resilience develops differ across contexts. The results also highlight that sociocultural aspects play an important role in the communicative processes of resilience. However, this study is limited in capturing the detailed impact of socio-cultural aspects on the communicative processes of resilience. It is recommended that tourism village actors, particularly local governments, integrate socio-cultural aspects when formulating disaster risk reduction strategies.


  • Reading between modalities: multimodal hate speech detection in low-resource Indonesian social media

    by Endang Wahyu Pamungkas, Arida Ferti Syafiandini, Dian Purworini, Widi Widayat, Divi Galih Prasetyo Putri, Ikhlasul Amal, Min Song


  • Open Access

    Decoding hate in memes: multimodal and multitask approaches for low-resource Indonesian social media

    by Endang Wahyu Pamungkas, Cahyaningtyas Sekar Wahyuni, Ikhlasul Amal, Dian Purworini, Bagus Setya Rintyarna

    Memes have become a dominant medium of online expression, blending humor, satire, and cultural commentary through visual and textual elements. While often used for entertainment and community building, memes can propagate hate speech in subtle and implicit ways, making automatic detection particularly challenging. This study introduces the Indonesian Multimodal Meme Dataset (INDOMEME), the first expert-annotated multimodal dataset for hateful meme detection in the Indonesian language. The dataset contains 5,023 memes collected from Facebook and annotated under three complementary schemes: hatefulness, appropriateness, and topical focus. Each meme is further enriched with optical character recognition (OCR) text and machine-generated captions, providing a comprehensive resource for multimodal analysis. Using this dataset, the study conducts extensive experiments addressing four research questions. First, unimodal models (text-only and image-only) are benchmarked against multimodal fusion models, showing that multimodal approaches outperform unimodal baselines; the best multimodal model (IndoBERTweet + Visual Transformers (ViT)) achieves a macro-F1 of 0.820 on hate speech detection and 0.809 on appropriateness classification. Second, several state-of-the-art multimodal large language models (MLLMs), including GPT-4o, Gemini 2.5 Flash, and Gemma3 27B, are evaluated in zero-shot settings, with GPT-4o reaching a macro-F1 of 0.772 for appropriateness detection, although MLLMs remain less effective for hatefulness classification compared to supervised approaches. Finally, multitask learning is explored by jointly modeling appropriateness and hatefulness using a dual-head architecture, demonstrating consistent performance gains across text-only models. These findings underscore the benefit of multimodal resources and multitask architectures in advancing Indonesian meme hate speech detection.


  • Open Access

    Enhancing Hate Speech Detection in Low-Resource Code-Mixed Indonesian Tweets via GPT-Based Data Augmentation

    by Endang Wahyu Pamungkas, Dian Purworini, Widi Widayat, Divi Galih Prasetyo Putri, Ikhlasul Amal

    Automatic hate speech detection in low-resource, code-mixed languages, such as Indonesian social media environments, presents significant challenges due to the scarcity of annotated data and the linguistic variability introduced by code-mixing. However, due to the growing prevalence of hate speech on social media, there is a need for robust hate speech detection systems. This study investigates the effectiveness of data augmentation strategies, specifically Generative Pretrained Transformer (GPT)-based paraphrasing and aggressive text transformation, in enhancing the performance of hate speech detection models for Indonesian code-mixed tweets. To achieve that, we employed traditional machine learning models, Recurrent Neural Network (RNN)-based models, and transformer-based models to assess the impact of these augmentation strategies. Our findings reveal that GPT-generated data improve model performance, with transformer-based models, including Indonesian Bidirectional Encoder Representations from Transformers (IndoBERT) and the Cross-lingual Language Model Robustly Optimized BERT Pretraining approach (XLM-RoBERTa).


  • Open Access

    Crisis in digital era and brand sustainability: Analyzing the #whitelabapologize activism on social media

    by Rona Rizkhy Bunga Chasana, Dian Purworini, Riski Apriliani

    This research aims to examine how crisis information spreads on social media and leads to activism. The public perceives the Whitelab brand event, which collaborated with K-Pop idol Sehun, as fraught with issues. This has resulted in public protests and the emergence of the #whitelabapologize hashtag on Twitter. This qualitative research uses social network analysis (SNA) to understand the social network and actors surrounding the conversation. A total of 10,000 tweets using #whitelabapologize were extracted from Twitter using Netlytic on the crucial date of the event. The research results classify #whitelabapologize as hashtag activism. Individual actors and the fan bases of K-pop idols drive the conversations on this social network. The data also reveals that this activism follows the logic of connective action.

  • Open Access

    Transformasi Digital Menuju Responsive Website Menggunakan Content Management System

    by Maryam, Dian Purworini, Rona Rizky Bunga Chasanah, Widi Widayat, Diah Priyawati

    Pada era digital, organisasi perlu mengikuti perkembangan teknologi termasuk dalam menyediakan website informatif yang mempu menarik perhatian pengguna. Penelitian ini bertujuan mendeskripsikan transformasi organisasi dakwah dalam menyediakan informasi sebagai bagian dari strategi dakwah digital. Fokus utama yaitu pada penggunaan WordPress CMS sebagai solusi dalam meningkatkan responsivitas dan jangkauan pengguna. Pendekatan praktis dilakukan dengan menggunakan metode pengembangan web development life cycle, dimulai dari analisis kebutuhan hingga implementasi teknologi. Aspek yang diperhatikan mencakup desain responsif, integrasi konten, dan pengalaman pengguna. Uji fungsionalitas dengan metode blackbox menunjukkan bahwa sistem berfungsi sesuai dengan output yang diharapkan. Hasil penelitian mencerminkan kemudahan akses informasi, respons situs web yang optimal terhadap berbagai perangkat, serta meningkatnya keterlibatan pengguna. Sistem ini dapat menjadi model bagi organisasi lain yang ingin memanfaatkan teknologi serupa untuk mempeluas jangkauan dakwah.

  • Public Opinion Towards Organisational Crisis: Insights from the Cognitive Appraisal Theory

    by Dian Purworini, Rona Rizhky Bunga Chasana, Dimas Aryo Anggoro

    Social media such as X is often used during crises as a platform to obtain information and share opinions. For organisations, public opinion serves as a source of information to understand public emotions. Therefore, this study used the context of crisis communication regarding organisational problems, and sentiment analysis to categorise tweets and understand the tones of public sentiment. It also aimed to test public reactions in the form of tweets related to an internal case faced by Whitelab, a cosmetics, beauty and personal care company. To achieve these objectives, a sentiment analysis was conducted. The data were obtained from X between 7 and 10 November 2022, using certain hashtags. The results showed that out of 7,224 tweets, 4,992 had negative, 450 positive and 1,782 neutral tones. In this study, a chi-square test showed significant differences among the types of sentiment score. The tweets were dominated by negative emotions in assessing organisations experiencing what was a preventable crisis. The study’s findings suggest that organisations suffering internal crises and receiving negative public responses should respond quickly and consider public emotions when establishing a crisis response strategy. The answer should be aimed at transforming negative sentiment to positive sentiment and neutral sentiment into positive sentiment. As a result, it would increase support for the organisation while minimising the negative impact on its reputation.


  • Open Access

    Enhancing digital literacy in early childhood school teachers: Technology and analysis approaches based on social cognitive theory

    by Dian Purworini, Endang Wahyu Pamungkas, Gedala Mulliah Naidoo, Lelita Azaria Rahmadiva, Maryam, Rona Rizkhy Bunga Chasana, Sidiq Setyawan, Wili Astuti, Yanti Haryanti

    [Bahasa]: Era digital yang berkembang pesat berpengaruh terhadap penyelenggaraan pembelajaran di semua level pendidikan. Guru yang memiliki peran krusial dalam pembelajaran harus memiliki kemampuan yang adaptif terhadap perubahan tersebut. Namun, banyak guru khsusunya pada level Pendidikan Anak Usia Dini (PAUD) menghadapi tantangan dalam mengintegrasikan teknologi ke dalam proses pembelajaran dan pengajaran. Pengabdian kepada masyarakat ini bertujuan untuk meningkatkan literasi digital pada guru anak usia dini. Metode pelaksanaan pengabdian yaitu dengan melakukan workshop yang berisi deskripsi pemahaman literasi digital dan praktik membuat materi ajar melalui software digital. Eskperimen yang melibatkan 49 partisipan dari 20 PAUD dilakukan untuk mengukur efektivitas implementasi workshop literasi digital. Pengumpulan data dilakukan melalui penyebaran angket pretest dan posttest, observasi dan wawancara. Hasil program pengabdian ini menunjukkan bahwa pelatihan literasi digital memberikan peningkatan literasi digital pada guru. Temuan pengabdian ini menunjukkan bahwa efikasi diri dan faktor sosial memberikan kontribusi terhadap keberhasilan training dalam program. Pelaksanaan training digital literasi dengan mempertimbangkan elemen-elemen teori kognitif sosial menjadi alternatif untuk meningkatkan kompetensi guru PAUD dalam praktik mengajar. Kata Kunci: guru PAUD, literasi digital, pelatihan, kompetensi [English]: The rapid development of the digital era affects teaching and learning practices at all levels of education. Teachers who play a crucial role in learning must have adaptive skills to respond to these changes. However, integrating technology into the learning and teaching process remains challenging for teachers of Early Childhood Education (ECED). This community service program aims to improve digital literacy in early childhood teachers. The workshop method was used in this program through the introduction of digital literacy understanding and practice of creating teaching materials through digital software. An experiment involving 49 participants from 20 PAUD was conducted to measure the effectiveness of the digital literacy workshop implementation. Data were collected through pretest and posttest questionnaires, observations, and interviews. The results show that the training in this community service program can improve digital literacy in teachers. The findings show that self-efficacy and social factors contribute to the effectiveness of the training program. The findings show that self-efficacy and social factors contribute to the effectiveness of the training program. Digital literacy training for early childhood education teachers involving elements of social cognitive theory is an alternative way to improve their teaching and learning practice competence. Keywords: early childhood teacher, digital literacy, training, competency


  • Open Access

    The Effect of Exposure to Scientific Ads on TikTok on Buying Interest (Quantitative Study on Indonesian Scientific Followers)

    by Raihanil Jannah, Dian Purworini

    Advertising has become one of the special forms of communication to solve marketing tasks. Advertising is more than just sharing information with the public. Many platforms can be used as advertising platforms, including TikTok. TikTok was originally a short video-sharing platform, specifically lip sync and dance videos, but over time, TikTok developed into a full-featured video service with various types of content. Scientific Indonesia is one of the brands that uses TikTok as its advertising platform. This research uses the S-O-R Theory. This study aims to determine the effect of exposure to Skintific ads on TikTok on buying interest. This study used a quantitative descriptive method. The population of this study was 535,200 followers of the scientific Indonesian TikTok account. The sample in this study amounted to 215 people using the Purposive Sampling method. Data collection techniques using questionnaires in the form of Google Forms. Test the data using IBM SPSS Statistics 23. the results of this study show that exposure to scientific on TikTok has a positive impact on being interested what the collection. This study achieved results showing that exposure to scientific ads on TikTok (X) has a positive effect on Buying Interest (Y). This research is useful in providing information to brands to improve marketing communication, especially advertising further because the result of this research is an advertisement that is very influential on product buying interest. One of them is scientific, where the correlation value (R) is 0.511, and the value of R square X to Y is 0.261. This means that the contribution of exposure to Indonesian scientific advertisements on the TikTok application to buying interest is 26.1%. In comparison, the remaining 74.9% is influenced by other variables that are not studied. In addition, the value of sig. 0.000 < 0.05, where the conclusion H0 is rejected and Ha is accepted.