clustex/datasets/spam.json

Clustex is a lightweight text classification package designed to efficiently categorize text based on similarity metrics and learned token weights.

{
    "classifications": [
        "spam",
        "normal"
    ],
    "data": [
        {"text": "Вы выиграли миллион долларов! Получите его сейчас!", "classification": "spam"},
        {"text": "Привет, как твои дела?", "classification": "normal"},
        {"text": "Act fast! Limited-time offer on luxury watches!", "classification": "spam"},
        {"text": "Hello, are you coming to the party tonight?", "classification": "normal"},
        {"text": "¡Increíble descuento en productos electrónicos! Haz clic aquí.", "classification": "spam"},
        {"text": "Hola, ¿quieres ir al cine este fin de semana?", "classification": "normal"},
        {"text": "Gagnez de l'argent rapidement avec ce système magique!", "classification": "spam"},
        {"text": "Salut! Tu veux prendre un café cet après-midi?", "classification": "normal"},
        {"text": "限时优惠！点击这里获取您的奖金！", "classification": "spam"},
        {"text": "你好！今天的天气真好！", "classification": "normal"},
        {"text": "Jetzt sofort anmelden und kostenloses Geld erhalten!", "classification": "spam"},
        {"text": "Hallo, hast du Lust auf ein Treffen morgen?", "classification": "normal"},
        {"text": "Эксклюзивное предложение! Только сегодня получите приз!", "classification": "spam"},
        {"text": "Как твои планы на выходные?", "classification": "normal"},
        {"text": "Biggest sale of the year! Click to claim your reward!", "classification": "spam"},
        {"text": "Would you like to grab lunch together?", "classification": "normal"},
        {"text": "¡Hazte rico rápido con este sencillo truco!", "classification": "spam"},
        {"text": "¿Quieres charlar un rato?", "classification": "normal"},
        {"text": "Ajoutez votre numéro pour un accès spécial!", "classification": "spam"},
        {"text": "J'adore les promenades en plein air!", "classification": "normal"},
        {"text": "点击链接获取免费产品！", "classification": "spam"},
        {"text": "我刚看完了一本书，太有趣了！", "classification": "normal"},
        {"text": "Erhalten Sie sofortigen Zugang zu exklusiven Deals!", "classification": "spam"},
        {"text": "Ich liebe es, neue Dinge zu lernen!", "classification": "normal"},
        {"text": "Супер акция! Скидки до 90%, спешите!", "classification": "spam"},
        {"text": "Сегодня был замечательный день!", "classification": "normal"},
        {"text": "Claim your free iPhone now!", "classification": "spam"},
        {"text": "I had a wonderful weekend!", "classification": "normal"},
        {"text": "¡Recibe dinero por ver anuncios!", "classification": "spam"},
        {"text": "Nos vemos mañana!", "classification": "normal"},
        {"text": "Gagnez un voyage de luxe gratuitement!", "classification": "spam"},
        {"text": "Profitez de cette belle journée!", "classification": "normal"},
        {"text": "赢得免费比特币！", "classification": "spam"},
        {"text": "我很期待周末！", "classification": "normal"},
        {"text": "Exklusive Casino-Angebote nur für Sie!", "classification": "spam"},
        {"text": "Ich habe eine neue Serie begonnen!", "classification": "normal"},
        {"text": "Прямо сейчас получите деньги без вложений!", "classification": "spam"},
        {"text": "Мне понравилось обсуждение сегодня!", "classification": "normal"},
        {"text": "This is your last chance to claim rewards!", "classification": "spam"},
        {"text": "Are you free for a call later?", "classification": "normal"},
        {"text": "¡Grandes premios en efectivo te esperan!", "classification": "spam"},
        {"text": "Disfruté la conversación contigo.", "classification": "normal"},
        {"text": "Gagnez instantanément avec cette opportunité unique!", "classification": "spam"},
        {"text": "J’ai découvert un nouveau café!", "classification": "normal"},
        {"text": "点击这里获取独家优惠！", "classification": "spam"},
        {"text": "我很喜欢这部电影！", "classification": "normal"},
        {"text": "Jetzt anmelden und doppelten Gewinn erhalten!", "classification": "spam"},
        {"text": "Ich genieße die frische Luft.", "classification": "normal"},
        {"text": "Секретный метод получения богатства!", "classification": "spam"},
        {"text": "Я люблю готовить новые блюда!", "classification": "normal"},
        {"text": "Claim your cryptocurrency reward now!", "classification": "spam"},
        {"text": "Let’s meet up tomorrow!", "classification": "normal"},
        {"text": "Уникальная возможность увеличить доход!", "classification": "spam"},
        {"text": "Прочитал интересную статью сегодня!", "classification": "normal"},
        {"text": "Super discount! Limited-time offer!", "classification": "spam"},
        {"text": "Would you like to go on a trip?", "classification": "normal"},
        {"text": "¡Compra ahora y recibe un gran premio!", "classification": "spam"},
        {"text": "Nos vemos en el café más tarde.", "classification": "normal"},
        {"text": "Maximize your earnings with this secret method!", "classification": "spam"},
        {"text": "I really enjoyed our discussion today.", "classification": "normal"},
        {"text": "Gagnez un prix en vous inscrivant maintenant!", "classification": "spam"},
        {"text": "J’ai découvert un restaurant incroyable!", "classification": "normal"},
        {"text": "独家折扣，只限今天！", "classification": "spam"},
        {"text": "我刚学会了一个新技能！", "classification": "normal"},
        {"text": "Sichern Sie sich jetzt Ihr kostenloses Geschenk!", "classification": "spam"},
        {"text": "Ich freue mich auf das Wochenende.", "classification": "normal"}
    ]
}