کنفرانس مهندسی برق ایران

صفحه اصلی / سی امین کنفرانس بین المللی مهندسی برق

Multinomial Emoji Prediction Using Deep Bidirectional Transformers and Topic Modeling

نویسندگان :

Zahra Ebrahimian¹ Ramin Toosi² Mohammad Ali Akhaee³

1- دانشگاه تهران 2- دانشگاه تهران 3- دانشگاه تهران

کلمات کلیدی :

emoji prediction،social network analysis،topic modeling،BERT

چکیده :

Abstract—As social networks grow more prominent, emojis become highly popular with a huge number of users. The primary function of emojis is to fill in emotional cues that might otherwise be missing from textual communication. These days, emojis are considered to be a large part of popular culture around the world. As a consequence, proper use of emojis in text messages will make you more friendly. Recently, emoji prediction becomes a challenging task, due to the large number of classes and the lack of suitable datasets. In this paper, we propose a multimodal emoji prediction model using the contextual information and the visual information. We used the EfficientNetB7 network to extract information from the images. EfficientNetB7 gives us the 10 most likely classes for each image. Also, we used Latent Dirichlet Allocation (LDA) as topic modeling to find hidden topics in the text. The topics extracted by LDA are then combined with the BERT network to improve the performance of this network. On our collected dataset, we achieved 46% accuracy for five emojis and 36% accuracy for 10 emojis.

لیست مقالات

لیست مقالات بایگانی شده

پیش‌بینی بلندمدت بار فصلی شبکه برق با استفاده از روش سری‌ زمانی ETS

میلاد حاجی ابوالحسنی - محسن صفرزاده - زهرا عظیمی - سیدمرتضی میرباقری

تخمین افسردگی مبتنی بر صوت با استفاده از بانک فیلتر و شبکه عصبی ResNet

علی نیک خراسانی - محمدرضا اکبرزاده توتونچی - مجید غیورمبرهن

Simulation Analysis of Electrode Metal Influence on the Microcavity Effect in Organic Light-Emitting Diodes

Faezeh Rahimi - Mohammad Sedghi - Asghar Gholami

Control of optical bistability in one-dimensional photonic crystals with a central layer doped with Landa-type three-level atoms using atomic and laser parameters

Akbar Ashrafabadi - Siamak Khademi - Ghasem Naeimi

Floquet model of spatiotemporally modulated graphene-based structures

Mahsa Valizadeh - Leila Yousefi - MirFaez Miri

طراحی تنظیم‌کننده‌ی خروجی بهینه‌ی مبتنی بر یادگیری تقویتی ایمن با استفاده از تابع مانع کنترلی نمایی

سیدرضا اصغری - سعید شمقدری

Evaluating the effect of electric vehicle charging station locations on line flows:An analytical approach

Mohammad Hasan Nikkhah - Mahdi Samadi

Bidirectional Isolated DC/DC Dual-Active-Bridge Converters Optimum Soft-Switching Control Method for Electrical Vehicle Applications

Shokoufeh Valadkhani - Mojtaba Mirsalim - Gevork B. Gharehpetian

Adaptive Fault Tolerant Control in Time-Varying Formation of Multi-Agent Systems

Elham Bahrampour - Mohammad Tavazoei

Adaptive Smooth Super Twisting Sliding Mode Control for Parkinson's Tremor Treatment

Reyhaneh Valibeik - ّFatemeh Jahangiri - Mostafa Abedi

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2