Multimodal Multilingual Sentiment Analysis

Multimodal multilingual sentiment analysis involves analysing sentiments expressed in different modalities (such as text, images, audio) and across different languages. This complex task begins with integrating and representing diverse data types, including textual, visual, and auditory information. Text is processed using natural language techniques, images are analyzed through computer vision methods, and audio data is examined through audio-specific models. The representations from these modalities are then fused to create a comprehensive view of sentiment, considering emotional and contextual aspects. Language- agnostic approaches or multilingual embeddings ensure that the system can handle sentiments expressed in various languages. Machine learning or deep learning models are employed for sentiment analysis, which are trained, fine-tuned, and evaluated using appropriate metrics. The resulting system can be deployed for real-time sentiment analysis across a wide range of data, continuously improved through feedback and updates to adapt to evolving languages and sentiments. 

The multimodal multilingual sentiment analysis combines the analysis of sentiments expressed through text, images, and audio, accounting for diverse languages. This comprehensive approach integrates techniques from natural language processing and computer vision, involving the fusion of modality-specific representations to understand and interpret sentiments accurately. The system is designed to be adaptable to multiple languages, making it a powerful tool for real- time sentiment analysis across various data sources, with ongoing refinements to enhance its effectiveness and applicability in our interconnected, multilingual world. 

The primary objectives of this project encompass the development of an innovative real-time, context-aware system dedicated to detecting sentiment across multiple modalities, including text, audio, and video, thereby enhancing the scope of sentiment analysis in a multilingual context. 

Academic qualifications

A first-class honours degree, or a distinction at master level, or equivalent achievements ideally in Computer Science

English language requirement

If your first language is not English, comply with the University requirements for research degree programmes in terms of English language

.

Application process

Prospective applicants are encouraged to contact the supervisor, Dr Kia Dashtipour (k.dashtipour@napier.ac.uk) to discuss the content of the project and the fit with their qualifications and skills before preparing an application. 

Contact details

Should you need more information, please email SCEBERDL@napier.ac.uk.

The application must include: 

Research project outline of 2 pages (list of references excluded). The outline may provide details about

• Background and motivation, explaining the importance of the project, should be supported also by relevant literature. You can also discuss the applications you expect for the project results.
• Research questions or
• Methodology: types of data to be used, approach to data collection, and data analysis methods.
• List of references

The outline must be created solely by the applicant. Supervisors can only offer general discussions about the project idea without providing any additional support.

• Statement no longer than 1 page describing your motivations and fit with the project.
• Recent and complete curriculum vitae. The curriculum must include a declaration regarding the English language qualifications of the candidate.
• Supporting documents will have to be submitted by successful candidates.
• Two academic references (but if you have been out of education for more than three years, you may submit one academic and one professional reference), on the form can be downloaded here.

Applications can be submitted here. To be considered, the application must use:

• the advertised title as project title

Download a copy of the project details here