Tell Me What You Eat, and I Will Tell You Where You Come From: A Data Science Approach for Global Recipe Data on the Web
Abstract :-
Thousands of recipes, representing different national cuisines, from the site recipesource.com were analyzed with the aim of understanding the food culture of various countries by comparing the ingredients used in their food. The recipe analysis identified ingredients and their frequencies of use in the creation of unique recipes. Food Analyzer, the program developed in this study, used data from recipes to examine correlations between individual food ingredients in recipes. This study found that 1) each country or ethnic group used authentic ingredients that differed from others and 2) the groupings of these authentic ingredients were essentially location-dependent. The boundaries of food-relevant areas were closely related to levels of precipitation. Meaningful correlations characterizing the food culture of each area can be explained by these authentic ingredients in recipes.
Existing Systems:-
Information pertaining to ingredients, cooking methods, and new recipes by people of various races, cultures, and social classes are being added every day. The internet has become an accessible repository of new food information, ranging from highly general information to new scientific facts related to specific ingredients or foods drawn from the media, academic journals, and government and research institutions.For instance, one new trend is sharing dining-out experiences on photo-enabled social networks. In fact, people are increasingly interested in discovering and sharing new cuisines, and knowing more about different aspects of the food they consume. Another popular application is keeping a personal log of daily meals and food intake. Food photos are popular, but in general users annotate them poorly, either with rather useless tags (e.g. “today’s lunch”, “delicious”), not accurate or generic tags (e.g. “Italian food”, “yellow rice”) and even wrong tags. In fact, this is not surprising, as accurate photo annotation requires specific domain knowledge and manual textual input is time-consuming and prone to typos. Thus, automatic annotation from a photo taken with the smart phone is much more convenient for the user, and automatic tags are more accurate and useful for retrieval applications.
Disadvantage:
Reliable automatic food recognition can enable countless functionalities in these systems. Examples include automatic phototagging, image-based retrieval (e.g. recipe, dietary properties), recommendation (e.g. food, recipe, restaurant).In earlier food-based research, recipes were collected from cookbooks and manually typed into computers. Although these studies have revealed some interesting patterns of ingredient usage related to a number of different countries.
Proposed Systems:-
Thousands of recipes, representing different national cuisines, from the site recipesource.com were analyzed with the aim of understanding the food culture of various countries by comparing the ingredients used in their food. The recipe analysis identified ingredients and their frequencies of use in the creation of unique recipes. Food Analyzer, the program developed in this study, used data from recipes to examine correlations between individual food ingredients in recipes.ingredients with other regions to a greater extent and, hence, have lower authenticity scores. Figure 8 shows the sum of the authenticity values of the 10 most authentic ingredients from each country and region. As expected, the countries of Asia & the Pacific countries were ranked high and the European countries were ranked low. Indian cuisine has many ingredients that are high in authenticity.
Advantage:
The ingredient network (IN) is a graph whose nodes are ingredients used in recipes. If two ingredients are used together in a recipe, an edge connecting them is drawn. The weight of the edge is set as the number of co-occurrences in the recipes. (we use the term dish to emphasize that it is related to restaurants, and also more specific than the term food). This scenario has contextual information we can exploit ,since the ingredients, cooking style and presentation of dishes and which dishes (i.e. menu) are very restaurant specific, and restaurants are also naturally linked to a geo location.
IMPLEMENTATION
Implementation is the stage of the project when the theoretical design is turned out into a working system. Thus it can be considered to be the most critical stage in achieving a successful new system and in giving the user, confidence that the new system will work and be effective.
The implementation stage involves careful planning, investigation of the existing system and it’s constraints on implementation, designing of methods to achieve changeover and evaluation of changeover methods.
Modules:
They have following 3 moudles
Food Culture,
National Cuisine,
Recipe Analysis
Food Culture:-
The boundaries of food-relevant areas were closely related to levels of precipitation. Meaningful correlations characterizing the food culture of each area can be explained by these authentic ingredients in recipes.The food culture of China can be subcategorized into four regional types: Mandarin (e.g., Peking duck), Cantonese (e.g., kao ru zhu; roast suckling pig), Sichuan (e.g., mapo tofu), and Shanghai cuisine (e.g., mitten-crab dish). Japanese cuisine uses a great deal of seafood and noodles, and is famous for its use of fish and shellfish as main ingredients of sushi and sashimi; meat, on the other hand, serves as the main ingredient in shabu-shabu and tonkatsu. Various styles of noodles feature in a range of noodle, ramen and buckwheat noodle dishes. Foods in southeast Asia contain large amounts of spices, with spices such as coriander being highly typical. Southeast Asia's leading foods include nuoc mam, ttomyangkkung, and pho (Vietnamese noodle soup).Western European countries such as France, Italy, Britain and Germany, each have their own unique food cultures with a large variety of foods; these have influenced each other throughout history, leading to a common food culture in which bread, wine and cheese play a prominent role.
National Cuisine:-
A clustering algorithm is used to detect hidden relationships among national cuisines based on patterns of ingredient usage. The purpose of this algorithm was to group countries with similar ingredient patterns and ungroup other countries.The goal of the present study was to infer the identity of national cuisines based on thousands of internet recipes and, more specifically, their ingredients. In recent years, limitations on the availability of ingredients due to geographic location and seasonal base have been reduced as a result of developments in transportation, such as air or sea vessel shipments, and in agricultural practices, such as greenhouse farming.
Recipe Analysis
The recipe analysis identified ingredients and their frequencies of use in the creation of unique recipes. Food Analyzer, the program developed in this study, used data from recipes to examine correlations between individual food ingredients in recipes. This study found that 1) each country or ethnic group used authentic ingredients that differed from others and 2) the groupings of these authentic ingredients were essentially location-dependent.The goal of the present study was to infer relationships between various countries’ cuisines, focusing on food ingredients in particular, based on thousands of internet recipes. Specifically, we used information about ingredients appearing in recipes in our cross-country comparisons.
System Configuration:
HARDWARE REQUIREMENTS:
Hardware - Pentium
Speed - 1.1 GHz
RAM - 2GB
Hard Disk - 20 GB
Floppy Drive - 1.44 MB
Key Board - Standard Windows Keyboard
Mouse - Two or Three Button Mouse
Monitor - SVGA
SOFTWARE REQUIREMENTS:
Operating System: Windows
Technology: Java and J2EE
Web Technologies: Html, JavaScript, CSS
IDE : My Eclipse
Web Server: Tomcat
Tool kit : Android Phone
Database: My SQL 5.0
Java Version: J2SDK1.7
CONCLUSIONS
The goal of the present study was to infer the identity of national cuisines based on thousands of internet recipes and, more specifically, their ingredients. In recent years, limitations on the availability of ingredients due to geographic location and seasonal base have been reduced as a result of developments in transportation, such as air or sea vessel shipments, and in agricultural practices, such as greenhouse farming. The unique culinary identities of various countries or ethnic groups may therefore be gradually weakened, diluted or mixed due to such radical developments in international trade and transportation. However, the results from the present study demonstrate that national dishes still contain ingredients that are representative of a particular group. The ingredients of recipes are highly symbolic for national or ethnic groups. In other words, the use of specific food ingredients in recipes has been well preserved as part of the preservation of a food identity. The grouping of countries based on patterns of ingredient usage is essentially location-dependent and is closely related to the annual precipitation of the analyzed countries.