Fast-paced advancements in technology demand swift adaptation and presents new opportunities and challenges for the optimization of communication, especially for advertisers. Digitalization and new developments in ICT have brought significant changes to the ways in which information, especially promotional messages, is disseminated to consumers. Additionally, with explosive interests in anticipation of fully autonomous vehicles, this study identifies and addresses the potential to optimize communication in an under examined digital media environment – in-vehicle infotainment system. Therefore, this study proposes a text-image embedding method recommender system for the personalization of multimedia contents and advertisements for in-vehicle infotainment systems. Unlike most previous research, which focuses on textual-only or image-only analyses, the current study explores the understanding, development and application of text embedding models and image feature extraction methods simultaneously in the context of target advertisement research. Overall, this study highlights the need to adapt to the ever-evolving technological landscape to optimize communication in various digital media environments. With the proposed text-image embedding method, this study offers a unique approach to personalizing multimedia content and advertisements in the under-explored digital media environment of in-vehicle infotainment systems.

Images have invaded nearly every section of our daily lives, from newspapers and magazines to advertisements we see all around. The form that these images take usually is the photograph, accompanied by written (or spoken) words of some sort – and thus actually forming an interaction of text and images. The culmination of this interaction is the so-called “photographic essay”, a series of photographs depicting a specified topic accompanied by text, usually published in a magazine, in a book or on the internet. To understand the potential of both image and word, a close reading of the seminal photo-essay Let Us Pray Famous Men by Walker Evans and James Agee shows that words can be devoid of the logos, the “logic”, argumentative potential of language, whereas images on the other hand can be arranged to make sense in a logical way. Let Us Now Praise Famous Men is read as criticism of the photographic essay as it is used in magazines, a criticism that nonetheless shows why and how the interaction of images with the written word transforms real experiences into experiences of reality, how it makes information happen.

In the history of visual art the images were often combined with linguistic text, as it is exemplified by the early egyptian mural, medieval religious painting with biblical quotation and the cubist paintings in 20st century. In those works the image and text cooperated complementarily with each other, pursuing the representation of the real. But in the second half of 20st century the poststructuralists proclaimed that the real doesn't exist at all and it is no more than the construction pursued by the signs such as language and image. Facing the crisis of representation the role of image and text in the visual art should have been changed. One of the leading video artist Gary Hill explored in his single channel video works in 1980's the working mechanism of image and text and their interaction, treating them as open signifier, which can be related numerous changeable new meanings. He also concentrates his inquiries on the role and meaning of language within our culture and other human context and destructed the existing mechanism of representation, which based on the solid relationship between signifier and signified. So, in <Why Do Things Get in a Muddle> he questions paradox of the logic, which served to produce the meaning of the world. In <Incidence of Catastrophe> he showed that all the metaphysical basement of our experience are not in itself real but they are just constructed through the semiotic process of image and words. These aspects of his arts are in some degree influenced by intellectual disposition of conceptual art in 1970's years, which revolved around the language instead of images. But his works explored not only the language but also the images as sign. Therefore his approach differ from the conceptual art, which eliminated the retinal aspects from their work. His works also set themselves apart from the ideology critical provocative work in 1980's, which targeted specific political and social issues. As he himself reaffirmed, his work focused on semiotic process and revealed unreliability of the working mechanism of logic, on which all the value system in our world based. In this sense his work in 1980's could be called meta-semiotic work.